To improve the accuracy of predicting non-invasive blood glucose concentration in the near-infrared spectrum, we utilized the Particle Swarm Optimization (PSO) algorithm to optimize hyperparameters for the Multi-Kerne...To improve the accuracy of predicting non-invasive blood glucose concentration in the near-infrared spectrum, we utilized the Particle Swarm Optimization (PSO) algorithm to optimize hyperparameters for the Multi-Kernel Learning Support Vector Machine (MKL-SVR). With these optimized hyperparameters, we established a non-invasive blood glucose regression model, referred to as the PSO-MKL-SVR model. Subsequently, we conducted a comparative analysis between the PSO-MKL-SVR model and the PSO-SVR model. In a dataset comprising ten volunteers, the PSO-MKL-SVR model exhibited significant precision improvements, including a 16.03% reduction in Mean Square Error and a 0.29% increase in the Squared Correlation Coefficient. Moreover, there was a 0.14% higher probability of the Clark’s Error Grid Analysis falling within Zone A. Additionally, the PSO-MKL-SVR model demonstrated a faster operational speed compared to the PSO-SVR model.展开更多
The rational and effective implementation of epidemic prevention and control measures is crucial to controlling the spread of COVID-19, and vaccination is a key part to be considered in the development of epidemic pre...The rational and effective implementation of epidemic prevention and control measures is crucial to controlling the spread of COVID-19, and vaccination is a key part to be considered in the development of epidemic prevention and control strategies. In order to give full play to the greater role of vaccination strategies in epidemic prevention and control, more accurate and efficient vaccination strategies should be explored. Based on the classical SEIR dynamic model, this paper established a COVID-19 dynamic model of population age structure in the form of population grouping and combined with the transmission characteristics of the COVID-19 epidemic. An optimization model with the goal of minimizing daily infection was established to analyze the optimization studies on infection-related specificity of vaccination for different age groups under the condition of limited daily vaccine supply at the early stage of the epidemic, and to obtain the priority of vaccination strategies for Chinese age groups. And the effect of the heterogeneity of infection rate and hospitalization rate on the priority of vaccine allocation.展开更多
At present, the Omicron variant is still the dominant strain in the global novel coronavirus pneumonia pandemic, and has the characteristics of concealed transmission, which brings heavy pressure to the health systems...At present, the Omicron variant is still the dominant strain in the global novel coronavirus pneumonia pandemic, and has the characteristics of concealed transmission, which brings heavy pressure to the health systems of different countries. Omicron infections were first found in Chinese Mainland in Tianjin in December 2021, and Omicron epidemic broke out in many parts of China in 2022. In order to enable the country and government to make scientific and accurate decisions in the face of the epidemic, it is particularly important to predict and analyze the relevant factors of Omicron’s covert transmission. In this paper, based on the official data of Jilin City and the improved SEIR dynamic model, through parameter estimation, the contact infection probability of symptomatic infected persons in Omicron infected patients is 0.4265, and the attenuation factor is 0.1440. Secondly, the influence of infectious duration in different incubation periods, asymptomatic infected persons and other factors on the epidemic situation in this area was compared. Finally, the scale of epidemic development was predicted and analyzed.展开更多
Aiming at the problem of open set voiceprint recognition, this paper proposes an adaptive threshold algorithm based on OTSU and deep learning. The bottleneck technology of open set voiceprint recognition lies in the c...Aiming at the problem of open set voiceprint recognition, this paper proposes an adaptive threshold algorithm based on OTSU and deep learning. The bottleneck technology of open set voiceprint recognition lies in the calculation of similarity values and thresholds of speakers inside and outside the set. This paper combines deep learning and machine learning methods, and uses a Deep Belief Network stacked with three layers of Restricted Boltzmann Machines to extract deep voice features from basic acoustic features. And by training the Gaussian Mixture Model, this paper calculates the similarity value of the feature, and further determines the threshold of the similarity value of the feature through OTSU. After experimental testing, the algorithm in this paper has a false rejection rate of 3.00% for specific speakers, a false acceptance rate of 0.35% for internal speakers, and a false acceptance rate of 0 for external speakers. This improves the accuracy of traditional methods in open set voiceprint recognition. This proves that the method is feasible and good recognition effect.展开更多
In this work, a deep belief neural network model (DBN) was developed to classify doves, chickens, mice and sheep blood samples, which have many similarities in composition causing their spectra to look almost identica...In this work, a deep belief neural network model (DBN) was developed to classify doves, chickens, mice and sheep blood samples, which have many similarities in composition causing their spectra to look almost identical by visual comparison alone. The DBN model was formulated for the feature extraction from the pretreated fluorescence spectroscopy. Then, cross-validation results showed that the application of deep learning method made it possible to classify the blood fluorescence spectroscopy in a more precise way than previous methods. Especially, the classification accuracy of whole blood with 1% of concentration was up to 97.5%.展开更多
Since the beginning of March 2022,the epidemic due to the Omicron variant has developed rapidly in Jilin Province.To figure out the key controlling factors and validate the model to show the success of the Zero-COVID ...Since the beginning of March 2022,the epidemic due to the Omicron variant has developed rapidly in Jilin Province.To figure out the key controlling factors and validate the model to show the success of the Zero-COVID policy in the province,we constructed a Recursive Zero-COVID Model quantifying the strength of the control measures,and defined the control reproduction number as an index for describing the intensity of interventions.Parameter estimation and sensitivity analysis were employed to estimate and validate the impact of changes in the strength of different measures on the intensity of public health preventions qualitatively and quantitatively.The recursive Zero-COVID model predicted that the dates of elimination of cases at the community level of Changchun and Jilin Cities to be on April 8 and April 17,respectively,which are consistent with the real situation.Our results showed that the strict implementation of control measures and adherence of the public are crucial for controlling the epidemic.It is also essential to strengthen the control intensity even at the final stage to avoid the rebound of the epidemic.In addition,the control reproduction number we defined in the paper is a novel index to measure the intensity of the prevention and control measures of public health.展开更多
文摘To improve the accuracy of predicting non-invasive blood glucose concentration in the near-infrared spectrum, we utilized the Particle Swarm Optimization (PSO) algorithm to optimize hyperparameters for the Multi-Kernel Learning Support Vector Machine (MKL-SVR). With these optimized hyperparameters, we established a non-invasive blood glucose regression model, referred to as the PSO-MKL-SVR model. Subsequently, we conducted a comparative analysis between the PSO-MKL-SVR model and the PSO-SVR model. In a dataset comprising ten volunteers, the PSO-MKL-SVR model exhibited significant precision improvements, including a 16.03% reduction in Mean Square Error and a 0.29% increase in the Squared Correlation Coefficient. Moreover, there was a 0.14% higher probability of the Clark’s Error Grid Analysis falling within Zone A. Additionally, the PSO-MKL-SVR model demonstrated a faster operational speed compared to the PSO-SVR model.
文摘The rational and effective implementation of epidemic prevention and control measures is crucial to controlling the spread of COVID-19, and vaccination is a key part to be considered in the development of epidemic prevention and control strategies. In order to give full play to the greater role of vaccination strategies in epidemic prevention and control, more accurate and efficient vaccination strategies should be explored. Based on the classical SEIR dynamic model, this paper established a COVID-19 dynamic model of population age structure in the form of population grouping and combined with the transmission characteristics of the COVID-19 epidemic. An optimization model with the goal of minimizing daily infection was established to analyze the optimization studies on infection-related specificity of vaccination for different age groups under the condition of limited daily vaccine supply at the early stage of the epidemic, and to obtain the priority of vaccination strategies for Chinese age groups. And the effect of the heterogeneity of infection rate and hospitalization rate on the priority of vaccine allocation.
文摘At present, the Omicron variant is still the dominant strain in the global novel coronavirus pneumonia pandemic, and has the characteristics of concealed transmission, which brings heavy pressure to the health systems of different countries. Omicron infections were first found in Chinese Mainland in Tianjin in December 2021, and Omicron epidemic broke out in many parts of China in 2022. In order to enable the country and government to make scientific and accurate decisions in the face of the epidemic, it is particularly important to predict and analyze the relevant factors of Omicron’s covert transmission. In this paper, based on the official data of Jilin City and the improved SEIR dynamic model, through parameter estimation, the contact infection probability of symptomatic infected persons in Omicron infected patients is 0.4265, and the attenuation factor is 0.1440. Secondly, the influence of infectious duration in different incubation periods, asymptomatic infected persons and other factors on the epidemic situation in this area was compared. Finally, the scale of epidemic development was predicted and analyzed.
文摘Aiming at the problem of open set voiceprint recognition, this paper proposes an adaptive threshold algorithm based on OTSU and deep learning. The bottleneck technology of open set voiceprint recognition lies in the calculation of similarity values and thresholds of speakers inside and outside the set. This paper combines deep learning and machine learning methods, and uses a Deep Belief Network stacked with three layers of Restricted Boltzmann Machines to extract deep voice features from basic acoustic features. And by training the Gaussian Mixture Model, this paper calculates the similarity value of the feature, and further determines the threshold of the similarity value of the feature through OTSU. After experimental testing, the algorithm in this paper has a false rejection rate of 3.00% for specific speakers, a false acceptance rate of 0.35% for internal speakers, and a false acceptance rate of 0 for external speakers. This improves the accuracy of traditional methods in open set voiceprint recognition. This proves that the method is feasible and good recognition effect.
文摘In this work, a deep belief neural network model (DBN) was developed to classify doves, chickens, mice and sheep blood samples, which have many similarities in composition causing their spectra to look almost identical by visual comparison alone. The DBN model was formulated for the feature extraction from the pretreated fluorescence spectroscopy. Then, cross-validation results showed that the application of deep learning method made it possible to classify the blood fluorescence spectroscopy in a more precise way than previous methods. Especially, the classification accuracy of whole blood with 1% of concentration was up to 97.5%.
基金the National Natural Science Foundation of China,China(12101157,12126206)Natural Science Foundation of Jilin Province,China(20210101482JC)Natural Science Foundation of Heilongjiang Province,China(LH2021A003).
文摘Since the beginning of March 2022,the epidemic due to the Omicron variant has developed rapidly in Jilin Province.To figure out the key controlling factors and validate the model to show the success of the Zero-COVID policy in the province,we constructed a Recursive Zero-COVID Model quantifying the strength of the control measures,and defined the control reproduction number as an index for describing the intensity of interventions.Parameter estimation and sensitivity analysis were employed to estimate and validate the impact of changes in the strength of different measures on the intensity of public health preventions qualitatively and quantitatively.The recursive Zero-COVID model predicted that the dates of elimination of cases at the community level of Changchun and Jilin Cities to be on April 8 and April 17,respectively,which are consistent with the real situation.Our results showed that the strict implementation of control measures and adherence of the public are crucial for controlling the epidemic.It is also essential to strengthen the control intensity even at the final stage to avoid the rebound of the epidemic.In addition,the control reproduction number we defined in the paper is a novel index to measure the intensity of the prevention and control measures of public health.