Stopping Threshold Research Articles

Enhancing Efficacy in Breast Cancer Screening with Nesterov Momentum Optimization Techniques

In the contemporary landscape of healthcare, machine learning models are pivotal in facilitating precise predictions, particularly in the nuanced diagnosis of complex ailments such as breast cancer. Traditional diagnostic methodologies grapple with inherent challenges, including excessive complexity, elevated costs, and reliance on subjective interpretation, which frequently culminate in inaccuracies. The urgency of early detection cannot be overstated, as it markedly broadens treatment modalities and significantly enhances survival rates. This paper delineates an innovative optimization framework designed to augment diagnostic accuracy by amalgamating momentum-based optimization techniques within a neural network paradigm. Conventional machine learning approaches are often encumbered by issues of overfitting, data imbalance, and the inadequacy of capturing intricate patterns in high-dimensional datasets. To counter these limitations, we propose a sophisticated framework that integrates an adaptive threshold mechanism across an array of gradient-based optimizers, including SGD, RMSprop, adam, adagrad, adamax, adadelta, nadam and Nesterov momentum. This novel approach effectively mitigates oscillatory behavior, refines parameter updates, and accelerates convergence. A salient feature of our methodology is the incorporation of a momentum threshold for early stopping, which ceases training upon the stabilization of momentum below a pre-defined threshold, thereby pre-emptively preventing overfitting. Leveraging the Wisconsin Breast Cancer Dataset, our model achieved a remarkable 99.72% accuracy and 100% sensitivity, significantly curtailing misclassification rates compared to traditional methodologies. This framework stands as a robust solution for early breast cancer diagnosis, thereby enhancing clinical decision making and improving patient outcomes.

Use estimated signal and noise to adjust step size for image restoration

Image deblurring is a challenging inverse problem, especially when there is additive noise to the observation. To solve such an inverse problem in an iterative manner, it is important to control the step size for achieving a stable and robust performance. We designed a method that controls the progress of iterative process in solving the inverse problem without the need for a user-specified step size. The method searches for an optimal step size under the assumption that the signal and noise are two independent stochastic processes. Experiments show that the method can achieve good performance in the presence of noise and imperfect knowledge about the blurring kernel. Tests also show that, for different blurring kernels and noise levels, the difference between two consecutive estimates given by the new method tends to remain more stable and stay in a smaller range, as compared to those given by some existing techniques. This stable feature makes the new method more robust in the sense that it is easier to select a stopping threshold for the new method to use in different scenarios.

Implementation of statistical features of a Bayesian two-armed responsive adaptive randomization trial with post hoc analysis of time trend drift

ABSTRACT Bayesian adaptive designs with response adaptive randomization (RAR) have the potential to benefit more participants in a clinical trial. While there are many papers that describe RAR designs and results, there is a scarcity of works reporting the details of RAR implementation from a statistical point exclusively. In this paper, we introduce the statistical methodology and implementation of the trial Changing the Default (CTD). CTD is a single-center prospective RAR comparative effectiveness trial to compare opt-in to opt-out tobacco treatment approaches for hospitalized patients. The design assumed an uninformative prior, conservative initial allocation ratio, and a higher threshold for stopping for success to protect results from statistical bias. A particular emerging concern of RAR designs is the possibility that time trends will occur during the implementation of a trial. If there is a time trend and the analytic plan does not prespecify an appropriate model, this could lead to a biased trial. Adjustment for time trend was not pre-specified in CTD, but post hoc time-adjusted analysis showed no presence of influential drift. This trial was an example of a successful two-armed confirmatory trial with a Bayesian adaptive design using response adaptive randomization.

Reducing the Antigen Prevalence Target Threshold for Stopping and Restarting Mass Drug Administration for Lymphatic Filariasis Elimination: A Model-Based Cost-effectiveness Simulation in Tanzania, India and Haiti.

The Global Programme to Eliminate Lymphatic Filariasis (GPELF) aims to reduce and maintain infection levels through mass drug administration (MDA), but there is evidence of ongoing transmission after MDA in areas where Culex mosquitoes are the main transmission vector, suggesting that a more stringent criterion is required for MDA decision making in these settings. We use a transmission model to investigate how a lower prevalence threshold (<1% antigenemia [Ag] prevalence compared with <2% Ag prevalence) for MDA decision making would affect the probability of local elimination, health outcomes, the number of MDA rounds, including restarts, and program costs associated with MDA and surveys across different scenarios. To determine the cost-effectiveness of switching to a lower threshold, we simulated 65% and 80% MDA coverage of the total population for different willingness to pay per disability-adjusted life-year averted for India ($446.07), Tanzania ($389.83), and Haiti ($219.84). Our results suggest that with a lower Ag threshold, there is a small proportion of simulations where extra rounds are required to reach the target, but this also reduces the need to restart MDA later in the program. For 80% coverage, the lower threshold is cost-effective across all baseline prevalences for India, Tanzania, and Haiti. For 65% MDA coverage, the lower threshold is not cost-effective due to additional MDA rounds, although it increases the probability of local elimination. Valuing the benefits of elimination to align with the GPELF goals, we find that a willingness to pay per capita government expenditure of approximately $1000-$4000 for 1% increase in the probability of local elimination would be required to make a lower threshold cost-effective. Lower Ag thresholds for stopping MDAs generally mean a higher probability of local elimination, reducing long-term costs and health impacts. However, they may also lead to an increased number of MDA rounds required to reach the lower threshold and, therefore, increased short-term costs. Collectively, our analyses highlight that lower target Ag thresholds have the potential to assist programs in achieving lymphatic filariasis goals.

An adaptive threshold-selected symplectic geometry mode decomposition for application to multi-modulation complex fault signals

The signals obtained from complex mechanical systems are characterized by multilevel modulation and strong noise, which can lead to difficulties in fault feature extraction. Symplectic geometry mode decomposition (SGMD) proves to be a valid approach for decomposing signals. However, inaccurate threshold selection in the iterative decomposition process can compromise the quality of fault diagnosis results. To address the shortcomings of SGMD, this paper proposes adaptive SGMD with adaptive threshold selection for fault diagnosis. Based on minimum dispersion entropy indicators, correlation coefficient and stopping thresholds are adaptively chosen using the proposed enhanced dung beetle optimizer algorithm. Then the optimal symplectic geometry component (SGC) is filtered based on the value of the integrated indicators after decomposition. Finally, the optimal SGC is analyzed by envelope demodulation to extract gear fault information. Through simulation and experimental analysis, this method surpasses SGMD and other signal decomposition methods in the aspect of fault feature extraction and noise robustness. Additionally, the results indicate an increase in feature energy ratio by 2.14%–9.85% compared to SGMD. The paper demonstrates that the proposed method extracts the fault feature frequencies of gears more effectively in complex mechanical systems.

Phase 1b Trial Evaluating Tolerability and Activity of Targeted Fibroblast Growth Factor Receptor Inhibition in Localized Upper Tract Urothelial Carcinoma.

We initiated a biomarker-informed preoperative study of infigratinib, a fibroblast growth factor receptor (FGFR) inhibitor, in patients with localized upper tract urothelial carcinoma (UTUC), a population with high unmet needs and tumor with a high frequency of FGFR3 alterations. Patients with localized UTUC undergoing ureteroscopy or nephroureterectomy/ureterectomy were enrolled on a phase 1b trial (NCT04228042). Once-daily infigratinib 125 mg by mouth × 21 days (28-day cycle) was given for 2 cycles. Tolerability was monitored by Bayesian design and predefined stopping boundaries. The primary endpoint was tolerability, and the secondary endpoint was objective response based on tumor mapping, done after endoscopic biopsy and post-trial surgery. Total planned enrollment: 20 patients. Targeted sequencing performed using a NovaSeq 6000 solid tumor panel. From May 2021 to November 2022, 14 patients were enrolled, at which point the trial was closed due to termination of all infigratinib oncology trials. Two patients (14.3%) had treatment-terminating toxicities, well below the stopping threshold. Responses occurred in 6 (66.7%) of 9 patients with FGFR3 alterations. Responders had median tumor size reduction of 67%, with 3 of 5 patients initially planned for nephroureterectomy/ureterectomy converted to ureteroscopy. Median follow-up in responders was 24.7 months (14.9-28.9). In this first trial of targeted therapy for localized UTUC, FGFR inhibition was well tolerated and had significant activity in FGFR3 altered tumors. Renal preservation was enabled in a substantial proportion of participants. These data support the design of a biomarker-driven phase 2 trial of FGFR3 inhibition in this population with significant unmet clinical needs.

A New Criterion for Improving Convergence of Fuzzy C-Means Clustering

One of the most used algorithms to solve the fuzzy clustering problem is Fuzzy C-Means; however, one of its main limitations is its high computational complexity. It is known that the efficiency of an algorithm depends, among other factors, on the strategies for its initialization and convergence. In this research, a new convergence strategy is proposed, which is based on the difference of the objective function values, in two consecutive iterations, expressed as a percentage of its value in the next to the last one. Additionally, a new method is proposed to optimize the selection of values of the convergence or stop threshold of the algorithm, which is based on the Pareto principle. To validate our approach, a collection of real datasets was solved, and a significant reduction in the number of iterations was observed, without affecting significantly the solution quality. Based on the proposed method and the experiments carried out, we found it is convenient to use threshold values equal to 0.73 and 0.35 if a decrease in the number of iterations of approximately 75.2% and 64.56%, respectively, is wanted, at the expense of a reduction in solution quality of 2% and 1%, respectively. It is worth mentioning that, as the size of the datasets is increased, the proposed approach tends to obtain better results, and therefore, its use is suggested for datasets found in Big Data and Data Science.

Effects of duration of follow-up and lag in data collection on the performance of adaptive clinical trials.

Different combined outcome-data lags (follow-up durations plus data-collection lags) may affect the performance of adaptive clinical trial designs. We assessed the influence of different outcome-data lags (0-105 days) on the performance of various multi-stage, adaptive trial designs (2/4 arms, with/without a common control, fixed/response-adaptive randomisation) with undesirable binary outcomes according to different inclusion rates (3.33/6.67/10 patients/day) under scenarios with no, small, and large differences. Simulations were conducted under a Bayesian framework, with constant stopping thresholds for superiority/inferiority calibrated to keep type-1 error rates at approximately 5%. We assessed multiple performance metrics, including mean sample sizes, event counts/probabilities, probabilities of conclusiveness, root mean squared errors (RMSEs) of the estimated effect in the selected arms, and RMSEs between the analyses at the time of stopping and the final analyses including data from all randomised patients. Performance metrics generally deteriorated when the proportions of randomised patients with available data were smaller due to longer outcome-data lags or faster inclusion, that is, mean sample sizes, event counts/probabilities, and RMSEs were larger, while the probabilities of conclusiveness were lower. Performance metric impairments with outcome-data lags ≤45 days were relatively smaller compared to those occurring with ≥60 days of lag. For most metrics, the effects of different outcome-data lags and lower proportions of randomised patients with available data were larger than those of different design choices, for example, the use of fixed versus response-adaptive randomisation. Increased outcome-data lag substantially affected the performance of adaptive trial designs. Trialists should consider the effects of outcome-data lags when planning adaptive trials.

Information-Theoretic Neural Decoding Reproduces Several Laws of Human Behavior.

Human response times conform to several regularities including the Hick-Hyman law, the power law of practice, speed-accuracy trade-offs, and the Stroop effect. Each of these has been thoroughly modeled in isolation, but no account describes these phenomena as predictions of a unified framework. We provide such a framework and show that the phenomena arise as decoding times in a simple neural rate code with an entropy stopping threshold. Whereas traditional information-theoretic encoding systems exploit task statistics to optimize encoding strategies, we move this optimization to the decoder, treating it as a Bayesian ideal observer that can track transmission statistics as prior information during decoding. Our approach allays prominent concerns that applying information-theoretic perspectives to modeling brain and behavior requires complex encoding schemes that are incommensurate with neural encoding.

ATNAS: Automatic Termination for Neural Architecture Search

Neural architecture search (NAS) is a framework for automating the design process of a neural network structure. While the recent one-shot approaches have reduced the search cost, there still exists an inherent trade-off between cost and performance. It is important to appropriately stop the search and further reduce the high cost of NAS. Meanwhile, the differentiable architecture search (DARTS), a typical one-shot approach, is known to suffer from overfitting. Heuristic early-stopping strategies have been proposed to overcome such performance degradation. In this paper, we propose a more versatile and principled early-stopping criterion on the basis of the evaluation of a gap between expectation values of generalisation errors of the previous and current search steps with respect to the architecture parameters. The stopping threshold is automatically determined at each search epoch without cost. In numerical experiments, we demonstrate the effectiveness of the proposed method. We stop the one-shot NAS algorithms and evaluate the acquired architectures on the benchmark datasets: NAS-Bench-201 and NATS-Bench. Our algorithm is shown to reduce the cost of the search process while maintaining a high performance.

#3715 THE EFFECT OF DAPRODUSTAT ON INTRAVENOUS IRON USE IN PATIENTS WITH CKD-RELATED ANAEMIA ON DIALYSIS IN THE ASCEND TRIALS

Abstract Background and Aims Intravenous (IV) iron is frequently needed in patients with chronic kidney disease (CKD) to ensure sufficient iron is available for erythropoiesis. However high doses of IV iron and erythropoiesis stimulating agents (ESAs) may be associated with risks in these patients [1]. The hypoxia-inducible factor-prolyl hydroxylase domain inhibitor daprodustat was non-inferior to comparator ESAs for the primary endpoint of efficacy (change-in-Hb) in the multicentre, randomised, Phase 3 trials ASCEND-D (NCT02879305) [2] and ASCEND-TD (NCT03400033) [3], also for the safety (major adverse cardiovascular [CV] events) coprimary endpoint in ASCEND-D [2]. This analysis of ASCEND-D and ASCEND-TD compared daprodustat to active ESAs on measures of IV iron use in dialysis patients. Method Daprodustat and ESAs were compared in patients with CKD anaemia on haemodialysis/peritoneal dialysis (ASCEND-D); haemodialysis (ASCEND-TD). ASCEND-D (N = 2,964) was an open-label CV outcome study using daprodustat once daily, while ASCEND-TD (N = 407) was a double-blind, double-dummy, 52-week study investigating three times weekly dosing of daprodustat. In both studies, following randomisation, treatment dosage was titrated to achieve the Hb target range of 10.0–11.0g/dL, with Hb efficacy assessed during the evaluation period (EP), Weeks 28–52. All patients were required to have ferritin &amp;gt;100 ng/mL and/or transferrin saturation (TSAT) &amp;gt;20% at baseline for inclusion. Throughout the study, iron therapy was administered if ferritin was ≤100 ng/mL and/or TSAT was ≤20% so patients would remain iron replete throughout the study. Investigators chose the route and dose of iron administration per patient iron status and clinical judgement. Stopping threshold criteria of 800 ng/mL ferritin + TSAT &amp;gt;20%, or TSAT&amp;gt;40% were implemented to avoid iron overload, but investigators could stop administration of iron at levels below the protocol-defined stopping thresholds. The average monthly IV iron dose (mg)/patient to Week 52 was a principal secondary endpoint, while the proportion of patients who met iron management criteria with a decrease in monthly IV iron dose during the EP relative to baseline and until patients received first transfusion were exploratory endpoints. The baseline monthly IV iron dose was defined as the average monthly IV iron (mg) over the 16 weeks prior to randomisation for ASCEND-D and over the 12 weeks prior to randomisation for ASCEND-TD. Results The proportion of patients with IV iron use at baseline was similar in both treatment arms for ASCEND-D (64%) but lower in the daprodustat group in ASCEND-TD (63% vs 72% in the ESA group). In both studies the proportion of patients receiving IV iron during the EP decreased (ASCEND-D: daprodustat 49%, ESA 52%; ASCEND-TD: daprodustat 38%, ESA 40%). The average monthly IV iron dose during the EP and from Day 1 to Week 52 was lower than monthly IV iron dose at baseline, however daprodustat was not associated with a statistically significant reduction in monthly IV iron per patient to Week 52 vs ESA comparator (Table 1). After a period of IV iron requirements decreasing, based on adjustment to protocol-specified levels, IV iron dosage remained relatively stable for daprodustat and ESA (Figure 1). In ASCEND-D, 3 of 23 pre-defined subgroups (prior ESA dose group, ESA hyporesponders2, history of myocardial infarction) showed a trend towards heterogeneity (interaction p-value &amp;lt;0.1), with differences in monthly IV iron use in the prior ESA dose group receiving ≥7000 U/week (-21.2 mg/month) and in the ESA hyporesponder group (-31.7 mg/month) in favour of daprodustat. Fewer patients met the criteria for stopping iron while on daprodustat vs ESA, whereas the converse was observed in ASCEND-TD (Table 1). Conclusion In ASCEND-D and -TD, no clinically or statistically significant reduction in monthly IV iron use was seen with daprodustat vs ESA comparators, although there was a numerical decrease in the proportion of patients receiving IV iron during the EP for the daprodustat group in both studies.

Winning strategies of a gambling demon in a Brownian particle under a squeezing potential

The ability of a gambling demon to extract work with a prescribed stopping threshold of cumulative work is analyzed theoretically and realized experimentally in the paradigm system of a Brownian particle in a time-dependent squeezing potential. The mechanism for the demon to beat the second law of thermodynamics (having a negative dissipative work or win) is sorted out in detail by analyzing the statistics of the stopped trajectories. The obtained insights, together with the associated nonequilibrium properties, further lead to improved strategies of the time-dependent stopping threshold to enhance the winning profit, which is confirmed experimentally.

Thermal cycle performance of thermocline storage: numerical and experimental exergy analysis

The performance of a dual-media thermocline storage is studied in stationary periodic operation. Successive cycles are carried out until a stabilised behaviour is obtained. Numerical results are compared to experiments realised on a 107 kWh prototype combining thermal oil and alumina. Two performance indicators are studied: utilisation rate and exergy efficiency. The utilisation rate decreases as the thermocline thickens over the cycles, while the exergy efficiency increases over the cycles, mainly due to lower heat losses improving the energy efficiency. Experimental values stabilise around UR = 53% and ηex= 73% at the fifth cycle. A new indicator is introduced: the storage quality factor Ψs, which quantifies the exergy losses due to the process. Experiments and simulations show good agreement, with a slight underestimation of heat losses by the model. Exergetic performance of thermocline storage is thus validated experimentally on a prototype-scale setup in stationary periodic regime, with satisfying value: Ψs≈ 0.99. The influence of stop thresholds on performance is then examined numerically. The utilisation rate decreases with strict thresholds (κch=κd= 0.05) because it prevents the storage to be fully loaded and because the thermocline thickens over the cycles if not extracted from the tank. The exergy efficiency globally increases for hybrid threshold (strict during charge, soft during discharge), with a maximum of ηex= 96.5% for κch= 0.05, κd= 0.95. In that configuration, the time during which the storage is hot is minimised, decreasing heat losses. Besides, setting strict thresholds limits the variation of the outlet temperature and reduces exergy destruction.

Monoclinic-to-tetragonal transition in HfO2 induced by swift heavy ions: Effects of thermal spike and oxygen defects

Phase transition induced by swift heavy ions in HfO2 are detrimental to the reliability of HfO2-based aerospace devices. In this paper, the monoclinic to tetragonal phase transition in HfO2 has been simulated by molecular dynamics combined with the two-temperature model. The specific roles of thermal spike, oxygen defects, and their coupling effects which have been considered as the key factors contributing to the phase transition in HfO2 were reported. Thermal spike results in sharply enhanced atomic stress, triggering the phase transition. The introduction of oxygen vacancies leads to significant reduction in the stress and corresponding electronic stopping threshold for phase transition. In addition, the presence of the oxygen defects results in reduced thermal conductivity and stronger electron-phonon coupling, which enhances the energy transmission to the lattice and further lowers the electronic stopping threshold. Sufficient number of oxygen vacancies are necessary for the survival of tetragonal phase to reduce the average potential energy of atoms.

Optimization of Energy Saving and Fuel-Cell Durability for Range-Extended Electric Vehicle

For a fuel cell range-extended electric vehicle (FC-REEV), the fuel cell system can work at a fixed output power point, and it has high durability. However, the differences in output power and start–stop threshold can lead to a significant difference in energy loss and degradation of power sources. Based on the thermostat control strategy (TCS), the state of charge (SOC) of the battery is stabilized within a reasonable range. To obtain the lowest hydrogen consumption rate, the vehicle’s fuel economy is considered in the evaluation function. The artificial bee colony (ABC) optimization algorithm is then used to increase the driving range, and the conventional ABC-TCS (CABC-TCS) is proposed. However, the CABC-TCS leads to many start–stop times for fuel cells. To enhance the durability of the fuel cells, a penalty factor was added to the evaluation function, and a novel optimized ABC-TCS (OABC-TCS) is proposed. Different strategies were tested under federal test procedure (FTP)-72 and worldwide light-duty test procedure (WLTC) driving cycles. The results show that, compared with TCS, the optimized driving range of OABC-TCS in FTP-72 and WLTC conditions increased almost 10.59% and 10.3%. Compared with CABC-TCS, the start–stop times of OABC-TCS in FTP-72 and WLTC conditions decreased by 27.55 and 46.47 times/h, respectively.

Measuring City-Level Transit Accessibility Based on the Weight of Residential Land Area: A Case of Nanning City, China

A large body of research on transit accessibility emphasizes the importance of methods to simulating the real-world travel process. Few efforts have been made to conduct empirical research and comparative analysis of overall city-level transit accessibility. In addition, most of literatures utilize census tracts combined with the buffer method to estimate transit travel demand or available service areas, failing to take into account the reality that different land-uses have their own population. This research aims to develop an overall index of city-level transit accessibility based on the weight of residential land area. We integrated five types of destinations and the coverage of residential area within the transit stop service area to evaluate the overall structural problems of land use and public transportation in the process of urban development. Based on a case study on Nanning City, it was found that the weighted average travel distance is increased by 5.42 km, but the overall weighted travel time of the city is shortened by 7.65 min. In addition, an increase in coverage within the stop threshold and a decrease in the number of residential communities outside the threshold indicate that transit accessibility facilitates urban expansion. The empirical results show that the overall transit accessibility index can provide a reasonable measure criterion for the compact spatial structure and support urban strategic planning and address the problem of land use and public transport in the process of urban development.

Sequential Multi-Hypothesis Testing in Multi-Armed Bandit Problems: An Approach for Asymptotic Optimality

We consider a multi-hypothesis testing problem involving a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -armed bandit. Each arm’s signal follows a distribution from a vector exponential family. The actual parameters of the arms are unknown to the decision maker. The decision maker incurs a delay cost for delay until a decision and a switching cost whenever he switches from one arm to another. His goal is to minimise the overall cost until a decision is reached on the true hypothesis. Of interest are policies that satisfy a given constraint on the probability of false detection. This is a sequential decision making problem where the decision maker gets only a limited view of the true state of nature at each stage, but can control his view by choosing the arm to observe at each stage. An information-theoretic lower bound on the total cost (expected time for a reliable decision plus total switching cost) is first identified, and a variation on a sequential policy based on the generalised likelihood ratio statistic is then studied. Due to the vector exponential family assumption, the signal processing at each stage is simple; the associated conjugate prior distribution on the unknown model parameters enables easy updates of the posterior distribution. The proposed policy, with a suitable threshold for stopping, is shown to satisfy the given constraint on the probability of false detection. Under a continuous selection assumption, the policy is also shown to be asymptotically optimal in terms of the total cost among all policies that satisfy the constraint on the probability of false detection.

Interval timing: Modelling the break-run-break pattern using start/stop threshold-less drift–diffusion model

Animal interval timing is often studied through the peak interval (PI) procedure. In this procedure, the animal is rewarded for the first response after a fixed delay from the stimulus onset, but on some trials, the stimulus remains and no reward is given. The standard methods and models to analyse the response pattern describe it as break-run-break, a period of low rate response followed by rapid responding, followed by a low rate of response. The study of the pattern has found correlations between start, stop, and duration of the run period that hold across species and experiments.It is commonly assumed that to achieve the statistics with a pacemaker accumulator model, it is necessary to have start and stop thresholds. In this paper, we will develop a new model that varies response rate in relation to the likelihood of event occurrence, as opposed to a threshold, for changing the response rate. The new model reproduced the start and stop statistics that have been observed in 14 different PI experiments from 3 different papers. The developed model is also compared to the two-threshold Time-adaptive Drift–diffusion Model (TDDM), and the latest accumulator model subsuming the scalar expectancy theory (SET) on all 14 datasets. The results show that it is unnecessary to have explicit start and stop thresholds or an internal equivalent to break-run-break states to reproduce the individual trials statistics, the average behaviour, and the break-run-break analysis results. The new model also produces more realistic individual trials compared to TDDM.

An adaptive multiple time domain synchronous averaging method and its application in vibration signal feature enhancement

The time domain synchronous averaging (TSA) method is a typical time domain signal denoising method, which is widely used in the state detection of rotating machinery. In order to solve the difficult problem of extracting vibration signal features from strong interference, an adaptive multiple time domain synchronous averaging method based on signal period is proposed in this paper. In view of the blindness and randomness of period selection in the TSA method, a new evaluation index of periodic impulse characteristics is proposed. In this method, the signal is resampled then the iteration stop threshold is set, and then the calculation period of interest is determined by two cycle screening. Finally, reconstructed signals with enhanced features are obtained by copying and stitching. Experimental results show that the proposed method is robust and superior in the feature detection of rolling bearing vibration signals.

Mislearning from censored data: The gambler's fallacy and other correlational mistakes in optimal‐stopping problems

I study endogenous learning dynamics for people who misperceive intertemporal correlations in random sequences. Biased agents face an optimal‐stopping problem. They are uncertain about the underlying distribution and learn its parameters from predecessors. Agents stop when early draws are “good enough,” so predecessors' experiences contain negative streaks but not positive streaks. When agents wrongly expect systematic reversals (the “gambler's fallacy”), they understate the likelihood of consecutive below‐average draws, converge to overpessimistic beliefs about the distribution's mean, and stop too early. Agents uncertain about the distribution's variance overestimate it to an extent that depends on predecessors' stopping thresholds. I also analyze how other misperceptions of intertemporal correlation interact with endogenous data censoring.