Average Window Research Articles

Silica-bridged inorganic-organic hybrid membrane for efficient daytime radiative cooling

Passive daytime radiative cooling (PDRC) has been considered as a cost-effective technology for efficient energy consumption and utilization, in which the heat is directly delivered into the outer space (3 K) through reflection and radiation. To achieve the high-performance PDRC, textile-based porous membranes are widely employed as radiators, however, the PDRC efficiency affected by the mechanical robustness. Herein, inspired by natural spider silks, a micro-/nano-sized hierarchical membrane-based radiator, which is rationally constructed with the interconnected polyethylene oxide (PEO) nanofibers bridged by the robust silica (SiO2) microspheres, was fabricated with the assistance of electrospinning. This as-prepared membrane features a hierarchically porous structure and a strong interfacial binding, resulting in the optimal optical and mechanical properties. For example, in the presence of a silane coupling agent, the tensile strength and the toughness of the resultant organic–inorganic hybrid membrane are enhanced by 7.1 and 7.2 times, respectively, compared to the organic PEO-based membrane. Furthermore, the assembled radiator demonstrates a temperature difference between 16.1 and 27.4 °C, accompanied by an average solar reflectance of 95.6 % and an average atmospheric window emittance of 89.9 %. This work provides a promising solution for achieving daytime radiative cooling at a reasonable cost and this technology could be extended into a wide range of application fields, such as smart buildings and aerospace industries.

Fault severity identification of planetary gearbox based on refined composite multiscale diversity entropy

Planetary gearbox is a key component in modern industry. A sudden failure may cause disastrous consequences. Thus, accurately acquiring the fault severity can be of importance. Diversity entropy emerges as a promising feature extraction tool for monitoring the health condition. However, the original diversity entropy has the defect that the data length of multiple time series will shorten at deep scales, resulting in unstable complexity estimation at high scale. To overcome this defect, a new feature extraction method has been proposed named refined composite multiscale diversity entropy (RCMDE). The proposed RCMDE method combines moving average windows under each scale factor and the refined state probability to improve the statistical reliability, which allows the diversity entropy to explore more refined fault information hidden at deeper scales. The simulation and experiment results proved that the proposed method has the highest diagnostic accuracy with the best stability in fault severity identification of planetary gearbox.

An adaptive reweighted-Kurtogram for bearing fault diagnosis under strong external impulse noise

In vibration-based fault diagnosis of rotating machinery, strong impulse noise constitutes a widely encountered source of external interference, thereby posing significant challenges to the effective extraction of diagnostic information. In this context, an adaptive reweighted-Kurtogram (ARKurtogram) method is proposed. The bearing transient fault signatures are accurately extracted through two aspects – that is, precise frequency band division and robust band selection indicator. Specifically, we use the dual-tree complex wavelet packet transform (DTCWPT) as the band division tool and propose the sub-bands rearranged and ensemble DTCWPT which addresses the band disorder problem, yields far richer band division patterns and maintains excellent performance of DTCWPT in signal decomposition. Meanwhile, we introduce a robust indicator characterizing periodic fault impulses to accurately select the fault band. In comparison with the classical kurtosis and the advanced reweighted-kurtosis, this indicator is insensitive to strong external impulse noise and its calculation process contains a sliding window averaging approach which makes the calculation entirely automated without human intervention. The validity of the ARKurtogram is investigated with the analysis of vibration signals measured from fault-injection experiments. The comparisons with the classical fast Kurtogram method and the advanced Autogram method highlight the advantages of the method in extracting bearing transient fault signatures from complex signals with strong external impulse noise. It shows high potential in the application of industrial bearing fault diagnosis.

An Improved Self-Adaptive Flower Pollination-Backpropagation Neural Network for the State of Charge Estimation of Lithium-Ion Batteries with Output Sliding Average Window Strategy

With the rapid development of electric vehicles and green energy sources, the use of backpropagation neural network (BPNN) to precisely estimate the state of charge (SOC) in lithium-ion batteries has become a popular research topic. However, traditionally BPNN has low prediction accuracy and large output fluctuations. To address the shortcomings of BPNN, self-adaptive flower pollination algorithm (SFPA) was proposed to optimize the initial weights and thresholds of BPNN, and an output sliding average window (OSAW) strategy is proposed to smooth SOC outputs in this research, which SOC estimation method is named SFPA-BP-OSAW. In addition, the performance of the newly proposed method is compared with other common related algorithms under different working conditions to verify the effectiveness of SFPA-BP-OSAW. The experimental results show that the mean absolute error of SFPA-BP-OSAW is 0.771% and 0.897%, and the root mean square error is 0.236% and 0.37%, respectively, under HPPC and BBDST working conditions. Experimental data and error analysis show that the method proposed in this paper has fast convergence, high prediction accuracy, and curve smoothness.

Determinacy and E‐Stability with Interest Rate Rules at the Zero Lower Bound

AbstractWe evaluate and compare alternative interest rate rules, namely, average inflation targeting (AIT), price‐level targeting (PLT), and traditional inflation targeting rules, in a standard New Keynesian model that features recurring, transient zero lower bound regimes. We use determinacy and expectational stability (E‐stability) of equilibrium as the criteria for stabilization policy. We find that PLT policy, including nominal GDP targeting as a special case, most effectively promotes determinacy and E‐stability among the policy frameworks, whereas standard inflation targeting rules are prone to indeterminacy. AIT can induce determinacy and E‐stability effectively, provided the averaging window is sufficiently long.

Comment on “Five Decades of Observed Daily Precipitation Reveal Longer and More Variable Drought Events Across Much of the Western United States”

AbstractChanges in precipitation patterns with climate change could have important impacts on human and natural systems. Zhang et al. (2021, https://doi.org/10.1029/2020gl092293) report trends in daily precipitation patterns over the last five decades in the western United States, focusing on meteorological drought. They report that dry intervals (calculated at the annual or seasonal level) have increased across much of the southwestern U.S., with statistical assessment suggesting the results are statistically robust. However, Zhang et al. (2021, https://doi.org/10.1029/2020gl092293) preprocess their annual (or seasonal) averages to compute 5‐year moving window averages before using established statistical techniques for trend analysis that assume independence about some fixed trend. Here we show that the moving window preprocessing violates that independence assumption and inflates the statistical significance of their trend estimates. This raises questions about the robustness of their results. We conclude by discussing the difficulty of adjusting for spatial structure when assessing time trends in a regional context.

Perceiving Synchrony: Determining Thermal-tactile Simultaneity Windows.

In cutaneous displays in which both tactile and thermal signals are presented, it is important to understand the temporal requirements associated with presenting these signals so that they are perceptually synchronous. Such synchrony is important to provide realistic touch experiences in applications involving object recognition and social touch interactions. In the present experiment the temporal window within which tactile and warm thermal stimuli are perceived to occur at the same time was determined. A Simultaneity Judgment Task was used in which pairs of tactile and thermal stimuli were presented on the hand at varying stimulus onset asynchronies, and participants determined whether the stimuli were simultaneous or not. The results indicated that the average simultaneity window width was 1041 ms. The average point of subjective simultaneity (PSS) was -569 ms, indicating that participants perceived simultaneity best when the warm thermal stimulus preceded the tactile stimulus by 569 ms. These findings indicate that thermal and tactile stimuli do not need to be displayed simultaneously for the two stimuli to be perceived as being synchronous and therefore the timing of such stimuli can be adjusted to maximize the likelihood that they will both be perceived.

On the Predictability of the DJIA and S&P500 Indexes

We obtained from Standard and Poor�s Corporation the complete 126-year history of the Dow Jones Industrial Average (DJIA) daily closing prices. We are applying rolling window averaging and adaptive learning methodologies, coupled with robust estimation methods, to examine which are the best forecasting models over a broad range of economic and financial conditions during the life of the index, based on daily and monthly stock index prices, and daily, monthly, and semi-annual stock returns. Why is an AR(1) model a reasonable benchmark of stock prices? Why do we have it? What should be our forecasting benchmarks? Do we find forecasting improvements from the Hendry-Castle-Doornik-Clements approach using robust forecasting methodologies and saturation variables in the prices of the index? Given that the DJIA fell over 15% during the first half of 2022, is this one of the worst six-month periods ever? What has happened to the Dow, historically, during such periods in the past with regard to six-month, one-year, and three-year-ahead stock returns? Is capitalism dead or doomed? We report statistically significant forecasting improvement from saturation and robust forecasting techniques during the 1896�June 2022 period. We report forecast stock returns for the next six months and three years that are bullish. In the King�s English, June 30, 2022, was another excellent common stock buying opportunity and Capitalism is not dead.

The association between chrononutrition behaviors and muscle health among older adults: The study of muscle, mobility and aging.

Emerging studies highlight chrononutrition's impact on body composition through circadian clock entrainment, but its effect on older adults' muscle health remains largely overlooked. To determine the associations between chrononutrition behaviors and muscle health in older adults. Dietary data from 828 older adults (76 ± 5 years) recorded food/beverage amounts and their clock time over the past 24 h. Studied chrononutrition behaviors included: (1) The clock time of the first and last food/beverage intake; (2) Eating window (the time elapsed between the first and last intake); and (3) Eating frequency (Number of self-identified eating events logged with changed meal occasion and clock time). Muscle mass (D3-creatine), leg muscle volume (MRI), grip strength (hand-held dynamometer), and leg power (Keiser) were used as outcomes. We used linear regression to assess the relationships between chrononutrition and muscle health, adjusting for age, sex, race, marital status, education, study site, self-reported health, energy, protein, fiber intake, weight, height, and moderate-to-vigorous physical activity. Average eating window was 11 ± 2 h/day; first and last intake times were at 8:22 and 19:22, respectively. After multivariable adjustment, a longer eating window and a later last intake time were associated with greater muscle mass (β ± SE: 0.18 ± 0.09; 0.27 ± 0.11, respectively, p < 0.05). The longer eating window was also marginally associated with higher leg power (p = 0.058). An earlier intake time was associated with higher grip strength (-0.38 ± 0.15; p = 0.012). Chrononutrition behaviors, including longer eating window, later last intake time, and earlier first intake time were associated with better muscle mass and function in older adults.

Performance evaluation of multifunctional windows for commercial buildings under hot-humid climatic environments

The Multifunctional Window (MFW) is a novel solution for solar radiation optimal utilization in commercial buildings. The present work aims to evaluate the performance of the Multifunctional Window consisting of multi-glazed window, liquid-absorbing filter, and traditional photovoltaic for use in near-zero-energy commercial buildings. Fulfilling this goal, a simulation model using CFD code was developed to predict the effect of design parameters such as absorbing filter liquid types (Pure water-polyethylene glycol–water/Ag Nanofluid), liquid filter thickness (2–10 mm), and air gap thickness (5–15 mm) on window performance characteristics and building energy savings under hot and humid climates. Results showed that the water/Ag Nanofluid (NF) minimize the PV surface temperatures by up to 3.2 °C and increase the power saving by about 6.4–9.8 % in comparison to other tested fluids i.e., NF is the best liquid filter from viewpoint of total power saving. As the thickness of the liquid filter increases, the transmitted indoor visible light radiation reduces by 43.6% and the average room load decreases by 47.6%. The average interior window surface temperature and room load of MFW are 4.1% and 60.7% lower than Window with PV only, respectively. The proposed MFW has the highest energy performance compared to typically adopted glazing systems.

Analog Memory and Synaptic Plasticity in an InGaZnO-Based Memristor by Modifying Intrinsic Oxygen Vacancies.

This study focuses on InGaZnO-based synaptic devices fabricated using reactive radiofrequency sputtering deposition with highly uniform and reliable multilevel memory states. Electron trapping and trap generation behaviors were examined based on current compliance adjustments and constant voltage stressing on the ITO/InGaZnO/ITO memristor. Using O2 + N2 plasma treatment resulted in stable and consistent cycle-to-cycle memory switching with an average memory window of ~95.3. Multilevel resistance states ranging from 0.68 to 140.7 kΩ were achieved by controlling the VRESET within the range of -1.4 to -1.8 V. The modulation of synaptic weight for short-term plasticity was simulated by applying voltage pulses with increasing amplitudes after the formation of a weak conductive filament. To emulate several synaptic behaviors in InGaZnO-based memristors, variations in the pulse interval were used for paired-pulse facilitation and pulse frequency-dependent spike rate-dependent plasticity. Long-term potentiation and depression are also observed after strong conductive filaments form at higher current compliance in the switching layer. Hence, the ITO/InGaZnO/ITO memristor holds promise for high-performance synaptic device applications.

Improved T-wave detection in electrocardiogram signals based non-stationary wavelet transform and QRS complex cancellation with kurtosis analysis

Objective. The T-wave in electrocardiogram (ECG) signal has the potential to enumerate various cardiac dysfunctions in the cardiovascular system. The primary objective of this research is to develop an efficient method for detecting T-waves in ECG signals, with potential applications in clinical diagnosis and continuous patient monitoring. Approach. In this work, we propose a novel algorithm for T-wave peak detection, which relies on a non-decimated stationary wavelet transform method (NSWT) and involves the cancellation of the QRS complex by utilizing its local extrema. The proposed scheme contains three stages: firstly, the technique is pre-processed using a two-stage median filter and Savitzky–Golay (SG) filter to remove the various artifacts from the ECG signal. Secondly, the NSWT technique is implemented using the bior 4.4 mother wavelet without downsampling, employing 24 scale analysis, and involves the cancellation of QRS-complex using its local positions. After that, Sauvola technique is used to estimate the baseline and remove the P-wave peaks to enhance T-peaks for accurate detection in the ECG signal. Additionally, the moving average window and adaptive thresholding are employed to enhance and identify the location of the T-wave peaks. Thirdly, false positive T-peaks are corrected using the kurtosis coefficients method. Main results. The robustness and efficiency of the proposed technique have been corroborated by the QT database (QTDB). The results are also validated on a self-recorded database. In QTDB database, the sensitivity of 98.20%, positive predictivity of 99.82%, accuracy of 98.04%, and detection error rate of 1.95% have been achieved. The self-recorded dataset attains a sensitivity, positive predictivity, accuracy, and detection error rate of 99.94%, 99.96%, 99.90%, and 0.09% respectively. Significance. A T-wave peak detection based on NSWT and QRS complex cancellation, along with kurtosis analysis technique, demonstrates superior performance and enhanced detection accuracy compared to state-of-the-art techniques.

Ambient particulate matter and renal function decline in people with HIV/AIDS.

We aimed to explore the effect of particulate matter exposure on renal function in people with HIV/AIDS (PWHA). A total of 37 739 repeated measurements were conducted on eGFR levels, serum creatinine (Scr), and the triglyceride-glucose (TyG) index in 6958 PWHAs. The relationship between 1 and 28 day moving averages of particulate matter concentrations with Scr and eGFR was assessed using linear mixed-effects models. Modified Poisson regression models were employed to assess the associations of cumulative particulate matter exposure with the incidence of chronic kidney disease (CKD). Mediation analyses were used to examine the role of TyG index. Short-term exposure to particulate matter was related to reduced renal function. The strongest associations between exposure to particulate matter (PM) 1 , PM 2.5 , and PM 10 and percentage changes in eGFR were observed at 7-day moving average exposure windows, with a respective decrease of 0.697% (-1.008%, -0.386%), 0.429% (-0.637%, -0.220%), and 0.373% (-0.581%, -0.164%) per IQR increment. Long-term exposure to PM 1 , PM 2.5 , and PM 10 was positively linked with the incidence of CKD, with each IQR increment corresponding to fully adjusted RRs (95% CIs) of 1.631 (1.446-1.839), 1.599 (1.431-1.787), and 1.903 (1.665-2.175), respectively. TyG index-mediated 8.87, 8.88, and 7.58% of the relationship between cumulative exposure to PM 1 , PM 2.5 , and PM 10 and increased risk of CKD, respectively. Exposure to particulate matter among PWHAs is linked to reduced renal function, potentially contributing to increased CKD incidence, where the TyG index might serve as a partial mediator.

The effects of particle injections on the ring current development during the 7-8 September 2017 geomagnetic storm

In this study we investigate the role of particle injections on the ring current development during the 7-8 September 2017 geomagnetic storm by applying a temporally and spatially varying data-driven outer boundary condition in numerical simulations of the ring current with the Comprehensive Inner Magnetosphere-Ionosphere model. We quantify the role of particle injections by comparing the results from two simulation runs: one with the model outer boundary condition defined by measurements at their original time cadence, namely, 1.5 min, and one with the same boundary condition smoothed in time with a 2-h running average window. The comparison between these two runs reveals that the observed particle injections enhanced the electric field remarkably, which had a significant effect on the ring current development, namely, they 1) strengthened the ring current, 2) skewed the ring current distribution dawnward, 3) delayed the formation of the symmetric ring current by prolonging the duration of the partial ring current, and 4) caused a O+-richer ring current with a O+ dominant ring current distribution at the inner edge. Furthermore, these effects enhanced the energy deposition to the plasmasphere and ionosphere via heating by the ring current ions.

Fault feature detection of planet gear in multi-stage planetary gearbox based on angle compensation synchronous averaging

Planetary gearboxes are often used for power transmission in wind turbines. It makes the gear fault detection of planetary gearboxes very useful and necessary. Generally, windowed synchronous averaging (WSA) is a widely used method to detect planet gear failure in planetary gearboxes. However, the WSA is not directly suitable for the multi-stage planetary gearbox since different planetary stages are working together and vibrations from different stages are coupled to each other. The coupled interference is the synchronous interference, which cannot be reduced by the WSA. It makes the faulty planet gear of interest difficult to detect. To address this issue, an angle compensation synchronous averaging (ACSA) scheme is proposed. The equi-angle resampling is applied to the obtained vibration first. Then, the synchronous interference can be constructed by applying the synchronous averaging-based angle compensation strategy, and removed by subtracting it from the resampled vibration. Subsequently, the fast spectral kurtosis is utilized on the residual vibration to obtain the envelope signal. Next, the WSA is further applied to the residual vibration and envelope signal for constructing the synthetic vibration and synthetic envelope signal corresponding to the planet gear of interest. Finally, the narrowband demodulation and envelope analysis are used to detect planet gear failure. Experiments on a two-stage planetary gearbox positively support the ACSA scheme.

Denoising of Raman Spectra Using a Neural Network Based on Variational Mode Decomposition, Empirical Wavelet Transform, and Encoder-Bidirectional Long Short-Term Memory

Raman spectroscopy has been widely applied in numerous fields including bioanalysis, disease diagnosis, and molecular recognition, owing to its unique advantages of being non-invasive, rapid, and highly specific. However, the acquisition of Raman spectral data is often susceptible to various noise interferences, such as shot noise from the internal detector and dark current noise from the instrument. As a result, the weak Raman signals typically become arduous to discern, which affects the localization and identification of characteristic spectral peaks. This study investigates variational mode decomposition (VMD), empirical wavelet transform (EWT), and integrated encoder-bidirectional long short-term memory (EBiLSTM) modules to propose a neural network algorithm for adaptive denoising of Raman spectra. By combining VMD and EWT, the Raman spectra are decomposed into several sub-sequences, which solves the problem of mode mixing between high-frequency signals and noise in empirical mode decomposition, and significantly reduces the complexity of the original Raman spectral lines. The correlation coefficient between each modal component and the original signal is calculated along with the zero-crossing rate index to categorize the noise and signal sequences. Leveraging the linear differences between the ideal spectral lines and the noisy spectral curves, an encoder-bidirectional long short-term memory (EBiLSTM) denoising network is constructed for hierarchical denoising to extract valid spectral feature information from the high-frequency components, realizing refined adaptive denoising of the Raman spectra. Industry standard objective evaluation metrics on the signal-to-noise ratio and root mean square error are utilized to conduct simulation experiments comparing state-of-the-art algorithms, including empirical mode decomposition, VMD, sliding window averaging, and wavelet thresholding. The experimental results demonstrate that the Raman spectral denoising algorithm combining variational mode decomposition and neural networks improves the denoising performance by 13.38% to 72%, exhibiting higher accuracy and reliability.

Novel insights into the NOx emissions characteristics in PEMS tests of a heavy-duty vehicle under different payloads

Real Drive Emission (RDE) test with Portable Emission Measurement System (PEMS) is a widely adopted way to assess vehicle emission compliance. However, the current NOx emissions calculation method stipulated in the China VI emission standard easily ignores the NOx emissions during cold start and low-power operation. To study the effect of cold start and low-power operation on the calculation of NOx emissions in the PEMS test, in this study, a China VI Heavy-Duty Vehicle (HDV) for urban use was used to conduct PEMS tests under various vehicle payload conditions. The data analysis results show that the increase in vehicle payload is beneficial to reducing the specific NOx emissions and passing the NOx emission compliance test because the increased payload improves the NOx conversion efficiency of the SCR system. Cold start duration has no obvious relationship with vehicle payload, accounting for only about 4∼6% in each test, but contributing more than 30% of NOx emissions. Due to the effect of the power threshold and the 90th cumulative percentile, the cold start data has little influence on the result of the NOx emissions assessment and the maximum variation of the NOx emissions result in this study is an 8% rise. For the HDV for urban use, the variation of the power threshold resulting from vehicle payload is small, no more than 2% in this study. The presence of the power threshold makes almost only the low-power operation in the second half of urban driving have an impact on the NOx emissions calculation, which may make more than 50% of NOx emissions in the PEMS test be neglected. The impact of the low-power operation on NOx emissions calculation result will be significantly enhanced if all windows are considered in the Moving Average Window (MAW) method. In the meantime, the degree of variation is closely related to the NOx emissions level during the first half of urban driving. The maximum deterioration of NOx emission assessment result can be more than 90% in this study.

On-road NOx and NH3 emissions measurements from in-use heavy-duty diesel and natural gas trucks in the South Coast air Basin of California

This study characterized nitrogen oxides (NOx) and ammonia (NH3) emissions from five in-use goods movement vehicles, including one diesel vehicle without selective catalytic reduction (SCR), two diesel vehicles with SCR, and two ultra-low NOx natural gas vehicles equipped with three-way catalysts (TWCs). Emissions testing was performed under real-world driving conditions in typical goods movement routes in the South Coast Air Basin (SCAB) of California. NOx emissions varied depending on the vehicle and the route. The no-SCR diesel vehicle showed the highest NOx emissions over all the routes. One of the SCR-equipped vehicles showed NOx emission rates that were two times higher than the other SCR-equipped vehicle with similar engine model year and mileage, which may be attributed to catalyst deterioration. The SCR-equipped diesel vehicles were within two to three times 0.2 g/bhp-hr certification standard over the different routes. The natural gas vehicles showed average NOx emissions around or below the optional Low NOx emissions standard of 0.02 g/bhp-hr. The three-bin moving average window (MAW) method was utilized to show the NOx emissions across various modes of operation, including idle, low load, and medium/high load. The highest fraction of vehicle operation was found in either the low load or medium/high load bins, depending on the route. NOx emissions for each of the bins varied between different vehicles, and are further analyzed in this paper. NH3 emissions formation was favored for the TWC-equipped natural gas vehicles, which produced about 20 times more NH3 emissions than the SCR-equipped diesel vehicles.

Tidal harmonics retrieval using GNSS-R dual-frequency complex observations

Tidal analysis and methods for estimation and prediction of ocean tidal constitutes are essential in a large area of scientific disciplines, for example, navigation, onshore and offshore engineering, and production of green energy. Ground-based Global Navigation Satellite System-Reflectometry (GNSS-R) has been proposed as an alternative method for measuring sea surface height. We use 6 years of GNSS-R observations at In-phase and Quadrature levels from July 2015 to May 2021 obtained from a dedicated receiver and sea-looking left hand circular polarization antenna for estimating sea level (SL). In the first step, the multivariate least-square harmonic estimation (LS-HE) method is applied for SL estimation. Then, final SL time series are generated by combining estimated SL from all satellites at L1 and L2 frequencies in the averaging step. The 6-year root-mean-square error between GNSS-R L12 sea surface heights and a collocated tide gauge (TG) is 5.8 cm with a correlation of 0.948 for a high temporal resolution of 5 min with 15 min averaging window. Afterward, using the univariate LS-HE, we detect tidal harmonics with periods between 30 min to 1 year. The detection results highlight a good match between GNSS-R and TG. Higher harmonics, i.e., the periods shorter than 3 h, show stronger signatures in GNSS-R data. Finally, we estimate the amplitude and phase of standard tidal harmonics from the two datasets. The results show an overall good agreement between the datasets with a few exceptions.

Pattern Analysis of Daily Lesion Volume Trajectories for Early Prediction of Glioblastoma Progression During MR-Linac Radiotherapy

Distinguishing between true progression (TP) and pseudoprogression (PP) post-radiotherapy (RT) is of paramount importance for treatment management of patients with glioblastoma (GBM). MR-Linac systems allow for daily monitoring of tumor changes throughout the course of RT. We hypothesized that the patterns of tumor volume change during RT may enable early prediction of treatment response. Using an IRB-approved prospective cohort of GBM patients undergoing 30 fractions of chemoRT to 60 Gy on a 0.35T MR-Linac, tumor/edema (tumor lesion) regions of interest (ROI) were contoured on daily T2-weighted treatment set-up scans. The obtained tumor lesion (TL) volume changes during treatment were smoothed with a moving average Gaussian window over time. Non-negative Matrix Factorization (NMF) was applied to the data matrix D (N x F), containing the trajectories in its rows for each patient, where N is the number of patients analyzed and F is the number of fractions. NMF represents D as a linear combination of three temporal (hidden) patterns and their weights in each individual trajectory. The same analysis was performed for ΔD, containing the changes in volumes with reference to the first fraction. The calculated weights were scaled in [0, 1], expressed as probabilities (by ℓ1-normalization) and used as features in Linear Discriminant Analysis (LDA). The LDA model was trained to differentiate between no progression (NP), PP and TP, and assessed by leave-one-subject-out cross-validation. Thirty-six patients were screened for inclusion: 9 were excluded due to no T2 lesion (resection cavity only). Of the remaining 27 GBM patients analyzed, 10 had no tumor growth on first post-RT diagnostic MRI, 6 were determined to have PP based on regression or long-term stability of findings, and 11 had TP due to continued progression of disease past 6 months, rapid patient death from disease, or tissue sampling showing active malignancy. With the use of only 2 features, LDA achieved an overall accuracy of 70.4% classifying correctly: 6 (60%), 4 (67%), and 9 (82%) patients with NP, PP, and TP, respectively. The temporal NMF patterns (monotonous decrease, rapid increase during the third part of the treatment, etc.) indicate that there is enough signal to classify patients' response based on the pattern tumor volume changes during RT. We identified tumor dynamics' patterns during RT, indicative of differential behavior of tumor growth between TP and PP. Although with a limited number of patients, these initial results suggest that tumor volume changes during treatment may provide early markers of treatment response. This could allow physicians to adapt/intensify treatment in real time for poorly responding patients. Next steps include automating the process of real-time tumor volume monitoring by incorporating a deep learning solution for automatic volume delineation on daily treatment set-up scans.