Purpose Anomaly detection is the process of identifying behaviors or events that do not meet expectations in data.High-power pulse energy systems are crucial technologies in numerous large-scale scientific devices.The...Purpose Anomaly detection is the process of identifying behaviors or events that do not meet expectations in data.High-power pulse energy systems are crucial technologies in numerous large-scale scientific devices.These systems utilize capacitors as energy storage units and can assess the condition of energy modules by analyzing discharge waveforms.Methods The range of values for different types of discharge waveforms varies significantly,and their distribution shows notable deviations.In this paper,we propose a long short-term memory-based encoder–decoder(LSTM-ED)framework for waveform anomaly detection,which effectively addresses the aforementioned issues.Results and conclusion Our method is divided into two stages,utilizing the mapping and recognition capabilities of the LSTM-ED model during the prediction stage.In the detection stage,we identify anomalies by setting different statistical thresholds for different circuits and types of discharge waveforms.Finally,a case study was conducted using real-time monitoring data from the energy module to validate the effectiveness of the proposed method.The results demonstrated that our approach can effectively identify anomalies across different types of discharge waveforms.展开更多
Gene transcription is a stochastic process characterized by fluctuations in mRNA levels of the same gene in isogenic cell populations.A central question in single-cell studies is how to map transcriptional variability...Gene transcription is a stochastic process characterized by fluctuations in mRNA levels of the same gene in isogenic cell populations.A central question in single-cell studies is how to map transcriptional variability to phenotypic differences between isogenic cells.We introduced a measurable and statistical transcription threshold I for critical genes that determine the entry level of Waddington’s canal toward a specific cell fate.Subsequently,J_(I),which is the probability that a cell has at least I mRNA molecules of a given gene,approximates the likelihood of a cell committing to the corresponding fate.In this study,we extended the previous results of J_(I) of the classical telegraph model by considering more complex models with different gene activation frameworks.We showed that(a)the upregulation of the critical gene may significantly suppress cell fate change and(b)increasing transcription noise performs a bidirectional role that can either enhance or suppress the cell fate change.These observations matched accurately with the data from bacterial,yeast,and mammalian cells.We estimated the threshold I from these data and predicted that(a)the traditional human immunodeficiency virus(HIV)activators that modulate gene activation frequency at high doses may largely suppress HIV reactivation and(b)the cells may favor noisier(or less noisy)regulation of stress genes under high(or low)environmental pressures to maintain cell viability.展开更多
文摘Purpose Anomaly detection is the process of identifying behaviors or events that do not meet expectations in data.High-power pulse energy systems are crucial technologies in numerous large-scale scientific devices.These systems utilize capacitors as energy storage units and can assess the condition of energy modules by analyzing discharge waveforms.Methods The range of values for different types of discharge waveforms varies significantly,and their distribution shows notable deviations.In this paper,we propose a long short-term memory-based encoder–decoder(LSTM-ED)framework for waveform anomaly detection,which effectively addresses the aforementioned issues.Results and conclusion Our method is divided into two stages,utilizing the mapping and recognition capabilities of the LSTM-ED model during the prediction stage.In the detection stage,we identify anomalies by setting different statistical thresholds for different circuits and types of discharge waveforms.Finally,a case study was conducted using real-time monitoring data from the energy module to validate the effectiveness of the proposed method.The results demonstrated that our approach can effectively identify anomalies across different types of discharge waveforms.
基金The National Natural Science Foundation of China,Grant/Award Numbers:12271118,12331017。
文摘Gene transcription is a stochastic process characterized by fluctuations in mRNA levels of the same gene in isogenic cell populations.A central question in single-cell studies is how to map transcriptional variability to phenotypic differences between isogenic cells.We introduced a measurable and statistical transcription threshold I for critical genes that determine the entry level of Waddington’s canal toward a specific cell fate.Subsequently,J_(I),which is the probability that a cell has at least I mRNA molecules of a given gene,approximates the likelihood of a cell committing to the corresponding fate.In this study,we extended the previous results of J_(I) of the classical telegraph model by considering more complex models with different gene activation frameworks.We showed that(a)the upregulation of the critical gene may significantly suppress cell fate change and(b)increasing transcription noise performs a bidirectional role that can either enhance or suppress the cell fate change.These observations matched accurately with the data from bacterial,yeast,and mammalian cells.We estimated the threshold I from these data and predicted that(a)the traditional human immunodeficiency virus(HIV)activators that modulate gene activation frequency at high doses may largely suppress HIV reactivation and(b)the cells may favor noisier(or less noisy)regulation of stress genes under high(or low)environmental pressures to maintain cell viability.
