scholarly journals Mining Knowledge of Respiratory Rate Quantification and Abnormal Pattern Prediction

2021 ◽  
Author(s):  
Piotr Szczuko ◽  
Adam Kurowski ◽  
Piotr Odya ◽  
Andrzej Czyżewski ◽  
Bożena Kostek ◽  
...  
Keyword(s):  
Signal Analysis ◽  
Granular Computing ◽  
Nearest Neighbor ◽  
Prediction Models ◽  
Respiratory Pattern ◽  
Breathing Patterns ◽  
K Nearest Neighbor ◽  
Normal Breathing ◽  
Abnormal Pattern ◽  
Male Sex

AbstractThe described application of granular computing is motivated because cardiovascular disease (CVD) remains a major killer globally. There is increasing evidence that abnormal respiratory patterns might contribute to the development and progression of CVD. Consequently, a method that would support a physician in respiratory pattern evaluation should be developed. Group decision-making, tri-way reasoning, and rough set–based analysis were applied to granular computing. Signal attributes and anthropomorphic parameters were explored to develop prediction models to determine the percentage contribution of periodic-like, intermediate, and normal breathing patterns in the analyzed signals. The proposed methodology was validated employing k-nearest neighbor (k-NN) and UMAP (uniform manifold approximation and projection). The presented approach applied to respiratory pattern evaluation shows that median accuracies in a considerable number of cases exceeded 0.75. Overall, parameters related to signal analysis are indicated as more important than anthropomorphic features. It was also found that obesity characterized by a high WHR (waist-to-hip ratio) and male sex were predisposing factors for the occurrence of periodic-like or intermediate patterns of respiration. It may be among the essential findings derived from this study. Based on classification measures, it may be observed that a physician may use such a methodology as a respiratory pattern evaluation-aided method.

scholarly journals Similarity-based error prediction approach for real-time inflow forecasting

2013 ◽  
Vol 45 (4-5) ◽  
pp. 589-602 ◽  
Author(s):  
Mahmood Akbari ◽  
Abbas Afshar
Keyword(s):  
Real Time ◽  
Nearest Neighbor ◽  
Prediction Models ◽  
Error Prediction ◽  
K Nearest Neighbor ◽  
Forecasting Models ◽  
Main Challenge ◽  
Inflow Forecasting ◽  
Artificial Neural Network Ann ◽  
Prediction Approach

Regardless of extensive researches on hydrologic forecasting models, the issue of updating the outputs from forecasting models has remained a main challenge. Most of the existing output updating methods are mainly based on the presence of persistence in the errors. This paper presents an alternative approach to updating the outputs from forecasting models in order to produce more accurate forecast results. The approach uses the concept of the similarity in errors for error prediction. The K nearest neighbor (KNN) algorithm is employed as a similarity-based error prediction model and improvements are made by new data, and two other forms of the KNN are developed in this study. The KNN models are applied for the error prediction of flow forecasting models in two catchments and the updated flows are compared to those of persistence-based methods such as autoregressive (AR) and artificial neural network (ANN) models. The results show that the similarity-based error prediction models can be recognized as an efficient alternative for real-time inflow forecasting, especially where the persistence in the error series of flow forecasting model is relatively low.

Optical SNR estimation using machine learning

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Palash Rai ◽  
Rahul Kaushik
Keyword(s):  
Machine Learning ◽  
Signal Analysis ◽  
Nearest Neighbor ◽  
Signal To Noise Ratio ◽  
Optical Signal ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbor ◽  
Eye Diagram ◽  
Test Instrument ◽  
Data Signal

Abstract A technique for the estimation of an optical signal-to-noise ratio (OSNR) using machine learning algorithms has been proposed. The algorithms are trained with parameters derived from eye-diagram via simulation in 10 Gb/s On-Off Keying (OOK) nonreturn-to-zero (NRZ) data signal. The performance of different machine learning (ML) techniques namely, multiple linear regression, random forest, and K-nearest neighbor (K-NN) for OSNR estimation in terms of mean square error and R-squared value has been compared. The proposed methods may be useful for intelligent signal analysis in a test instrument and to monitor optical performance.

scholarly journals Heartbeat Detection by Laser Doppler Vibrometry and Machine Learning

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5362 ◽  
Author(s):  
Luca Antognoli ◽  
Sara Moccia ◽  
Lucia Migliorelli ◽  
Sara Casaccia ◽  
Lorenzo Scalise ◽  
...  
Keyword(s):  
Machine Learning ◽  
Signal Analysis ◽  
Cross Validation ◽  
Nearest Neighbor ◽  
Laser Doppler Vibrometer ◽  
Laser Doppler ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Real World Application ◽  
Testing Protocol

Background: Heartbeat detection is a crucial step in several clinical fields. Laser Doppler Vibrometer (LDV) is a promising non-contact measurement for heartbeat detection. The aim of this work is to assess whether machine learning can be used for detecting heartbeat from the carotid LDV signal. Methods: The performances of Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) and K-Nearest Neighbor (KNN) were compared using the leave-one-subject-out cross-validation as the testing protocol in an LDV dataset collected from 28 subjects. The classification was conducted on LDV signal windows, which were labeled as beat, if containing a beat, or no-beat, otherwise. The labeling procedure was performed using electrocardiography as the gold standard. Results: For the beat class, the f1-score (f1) values were 0.93, 0.93, 0.95, 0.96 for RF, DT, KNN and SVM, respectively. No statistical differences were found between the classifiers. When testing the SVM on the full-length (10 min long) LDV signals, to simulate a real-world application, we achieved a median macro-f1 of 0.76. Conclusions: Using machine learning for heartbeat detection from carotid LDV signals showed encouraging results, representing a promising step in the field of contactless cardiovascular signal analysis.

scholarly journals An Enhanced K-Nearest Neighbor Predictive Model through Metaheuristic Optimization

2020 ◽  
Vol 10 (4) ◽  
pp. 280-292
Author(s):  
Allemar Jhone P. Delima
Keyword(s):  
Genetic Algorithm ◽  
Prediction Model ◽  
Prediction Accuracy ◽  
Nearest Neighbor ◽  
Prediction Models ◽  
Faculty Evaluation ◽  
The Novel ◽  
Improved Genetic Algorithm ◽  
K Nearest Neighbor ◽  
Negative Effects

The k-nearest neighbor (KNN) algorithm is vulnerable to noise, which is rooted in the dataset and has negative effects on its accuracy. Hence, various researchers employ variable minimization techniques before predicting the KNN in the quest so as to improve its predictive capability. The genetic algorithm (GA) is the most widely used metaheuristics for such purpose; however, the GA suffers a problem that its mating scheme is bounded on its crossover operator. Thus, the use of the novel inversed bi-segmented average crossover (IBAX) is observed. In the present work, the crossover improved genetic algorithm (CIGAL) is instrumental in the enhancement of KNN’s prediction accuracy. The use of the unmodified genetic algorithm has removed 13 variables, while the CIGAL then further removes 20 variables from the 30 total variables in the faculty evaluation dataset. Consequently, the integration of the CIGAL to the KNN (CIGAL-KNN) prediction model improves the KNN prediction accuracy to 95.53%. In contrast to the model of having the unmodified genetic algorithm (GA-KNN), the use of the lone KNN algorithmand the prediction accuracy is only at 89.94% and 87.15%, respectively. To validate the accuracy of the models, the use of the 10-folds cross-validation technique reveals 93.13%, 89.27%, and 87.77% prediction accuracy of the CIGAL-KNN, GA-KNN, and KNN prediction models, respectively. As the result, the CIGAL carried out an optimized GA performance and increased the accuracy of the KNN algorithm as a prediction model.

scholarly journals Frequency-Modulated Continuous Wave Radar Respiratory Pattern Detection Technology Based on Multifeature

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Qisong Wang ◽  
Zhening Dong ◽  
Dan Liu ◽  
Tianao Cao ◽  
Meiyan Zhang ◽  
...  
Keyword(s):  
Standard Deviation ◽  
Respiratory Diseases ◽  
Nearest Neighbor ◽  
Continuous Wave ◽  
Respiratory Pattern ◽  
Support Vector ◽  
Numerical Comparison ◽  
K Nearest Neighbor ◽  
Rectangular Window ◽  
Wave Radar

Respiratory diseases including apnea are often accompanied by abnormal respiratory depth, frequency, and rhythm. If different abnormal respiratory patterns can be detected and recorded, with their depth, frequency, and rhythm analyzed, the detection and diagnosis of respiratory diseases can be achieved. High-frequency millimeter-wave radar (76–81 GHz) has low environmental impact, high accuracy, and small volume, which is more suitable for respiratory signal detection and recognition compared with other contact equipment. In this paper, the experimental platform of frequency-modulated continuous wave (FMCW) radar was built at first, realizing the noncontact measurement of vital signs. Secondly, the energy intensity and threshold of respiration signal during each period were calculated by using the rectangular window, and the accurate judgment of apnea was realized via numerical comparison. Thirdly, the features of respiratory and heart rate signals, the number of peaks and valleys, the difference between peaks and valleys, the average and the standard deviation of normalized short-term energy, and the average and the standard deviation and the minimum of instantaneous frequency, were extracted and analyzed. Finally, support vector machine (SVM) and K-nearest neighbor (KNN) were used to classify the extracted features, and the accuracy was 98.25% and 88.75%, respectively. The classification and recognition of respiratory patterns have been successfully realized.

scholarly journals Booking Prediction Models for Peer-to-peer Accommodation Listings using Logistics Regression, Decision Tree, K-Nearest Neighbor, and Random Forest Classifiers

2020 ◽  
Vol 6 (2) ◽  
pp. 123
Author(s):  
Mochammad Agus Afrianto ◽  
Meditya Wasesa
Keyword(s):  
Random Forest ◽  
Decision Tree ◽  
Revenue Management ◽  
Nearest Neighbor ◽  
Prediction Models ◽  
Model Development ◽  
Peer To Peer ◽  
K Nearest Neighbor ◽  
Logistics Regression ◽  
Roc Score

Background: Literature in the peer-to-peer accommodation has put a substantial focus on accommodation listings' price determinants. Developing prediction models related to the demand for accommodation listings is vital in revenue management because accurate price and demand forecasts will help determine the best revenue management responses.Objective: This study aims to develop prediction models to determine the booking likelihood of accommodation listings.Methods: Using an Airbnb dataset, we developed four machine learning models, namely Logistics Regression, Decision Tree, K-Nearest Neighbor (KNN), and Random Forest Classifiers. We assessed the models using the AUC-ROC score and the model development time by using the ten-fold three-way split and the ten-fold cross-validation procedures.Results: In terms of average AUC-ROC score, the Random Forest Classifiers outperformed other evaluated models. In three-ways split procedure, it had a 15.03% higher AUC-ROC score than Decision Tree, 2.93 % higher than KNN, and 2.38% higher than Logistics Regression. In the cross-validation procedure, it has a 26,99% higher AUC-ROC score than Decision Tree, 4.41 % higher than KNN, and 3.31% higher than Logistics Regression.  It should be noted that the Decision Tree model has the lowest AUC-ROC score, but it has the smallest model development time.Conclusion: The performance of random forest models in predicting booking likelihood of accommodation listings is the most superior. The model can be used by peer-to-peer accommodation owners to improve their revenue management responses. 

scholarly journals A Systematic Methodology to Evaluate Prediction Models for Driving Style Classification

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1692 ◽  
Author(s):  
Iván Silva ◽  
José Eugenio Naranjo
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Performance Metrics ◽  
Prediction Models ◽  
Statistical Tests ◽  
Area Under The Curve ◽  
The Other ◽  
Support Vector ◽  
Classification Models ◽  
K Nearest Neighbor

Identifying driving styles using classification models with in-vehicle data can provide automated feedback to drivers on their driving behavior, particularly if they are driving safely. Although several classification models have been developed for this purpose, there is no consensus on which classifier performs better at identifying driving styles. Therefore, more research is needed to evaluate classification models by comparing performance metrics. In this paper, a data-driven machine-learning methodology for classifying driving styles is introduced. This methodology is grounded in well-established machine-learning (ML) methods and literature related to driving-styles research. The methodology is illustrated through a study involving data collected from 50 drivers from two different cities in a naturalistic setting. Five features were extracted from the raw data. Fifteen experts were involved in the data labeling to derive the ground truth of the dataset. The dataset fed five different models (Support Vector Machines (SVM), Artificial Neural Networks (ANN), fuzzy logic, k-Nearest Neighbor (kNN), and Random Forests (RF)). These models were evaluated in terms of a set of performance metrics and statistical tests. The experimental results from performance metrics showed that SVM outperformed the other four models, achieving an average accuracy of 0.96, F1-Score of 0.9595, Area Under the Curve (AUC) of 0.9730, and Kappa of 0.9375. In addition, Wilcoxon tests indicated that ANN predicts differently to the other four models. These promising results demonstrate that the proposed methodology may support researchers in making informed decisions about which ML model performs better for driving-styles classification.

scholarly journals Adaptive Multi-Type Fingerprint Indoor Positioning and Localization Method Based on Multi-Task Learning and Weight Coefficients K-Nearest Neighbor

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5416 ◽  
Author(s):  
Zhengwu Yuan ◽  
Xupeng Zha ◽  
Xiaojian Zhang
Keyword(s):  
Nearest Neighbor ◽  
Prediction Models ◽  
Weighted Average ◽  
Indoor Positioning ◽  
Positioning Error ◽  
K Nearest Neighbor ◽  
Localization Method ◽  
Task Learning ◽  
Positioning Errors ◽  
Weight Coefficients

The complex indoor environment makes the use of received fingerprints unreliable as an indoor positioning and localization method based on fingerprint data. This paper proposes an adaptive multi-type fingerprint indoor positioning and localization method based on multi-task learning (MTL) and Weight Coefficients K-Nearest Neighbor (WCKNN), which integrates magnetic field, Wi-Fi and Bluetooth fingerprints for positioning and localization. The MTL fuses the features of different types of fingerprints to search the potential relationship between them. It also exploits the synergy between the tasks, which can boost up positioning and localization performance. Then the WCKNN predicts another position of the fingerprints in a certain class determined by the obtained location. The final position is obtained by fusing the predicted positions using a weighted average method whose weights are the positioning errors provided by positioning error prediction models. Experimental results indicated that the proposed method achieved 98.58% accuracy in classifying locations with a mean positioning error of 1.95 m.

scholarly journals Predicting Learning Outcomes with MOOC Clickstreams

2019 ◽  
Vol 9 (2) ◽  
pp. 104 ◽  
Author(s):  
Chen-Hsiang Yu ◽  
Jungpin Wu ◽  
An-Chi Liu
Keyword(s):  
Machine Learning ◽  
Learning Outcomes ◽  
Prediction Accuracy ◽  
Nearest Neighbor ◽  
Prediction Models ◽  
Video Data ◽  
Support Vector ◽  
Completion Rates ◽  
K Nearest Neighbor ◽  
Learning Behaviors

Massive Open Online Courses (MOOCs) have gradually become a dominant trend in education. Since 2014, the Ministry of Education in Taiwan has been promoting MOOC programs, with successful results. The ability of students to work at their own pace, however, is associated with low MOOC completion rates and has recently become a focus. The development of a mechanism to effectively improve course completion rates continues to be of great interest to both teachers and researchers. This study established a series of learning behaviors using the video clickstream records of students, through a MOOC platform, to identify seven types of cognitive participation models of learners. We subsequently built practical machine learning models by using K-nearest neighbor (KNN), support vector machines (SVM), and artificial neural network (ANN) algorithms to predict students’ learning outcomes via their learning behaviors. The ANN machine learning method had the highest prediction accuracy. Based on the prediction results, we saw a correlation between video viewing behavior and learning outcomes. This could allow teachers to help students needing extra support successfully pass the course. To further improve our method, we classified the course videos based on their content. There were three video categories: theoretical, experimental, and analytic. Different prediction models were built for each of these three video types and their combinations. We performed the accuracy verification; our experimental results showed that we could use only theoretical and experimental video data, instead of all three types of data, to generate prediction models without significant differences in prediction accuracy. In addition to data reduction in model generation, this could help teachers evaluate the effectiveness of course videos.

Sign in / Sign up

Export Citation Format

Share Document