An Efficient Scene-Break Detection Method Based on Linear Prediction With Bayesian Cost Functions

Formant tracking linear prediction model using HMMs and Kalman filters for noisy speech processing

Advanced driver assistance systems have been an active research topic for decades, for which many approaches have been developed not only to reduce the number of traffic accidents but also to increase the driver’s comfort. Among the many different solutions proposed, learning-based prediction approaches have gained considerable attention in recent years. Within this scope, this work focuses on the implementation aspects of a linear learning-based regression model for detecting unintended lane-departures, where the goal is to achieve a prediction model with good predictive performance while keeping the computational complexity as low as possible. Aspects under consideration include input signal selection and down-sampling. The linear prediction model is analyzed using a real world data set, and benchmarked against a kinematic constant velocity model and a non-linear regression model. The results show that the linear regression model has a significantly higher prediction performance when compared to a kinematic model. It is also shown that the predictive performance remains comparable to the more complex nonlinear regression model, even though the computational complexity of the linear model is significantly lower.

Both Chinese and foreign researchers have developed linear models to predict track irregularities. These models adopt the Track Quality Index (TQI) as an index to evaluate overall track irregularity. In these models, an averaging method is employed to calculate the slope k of track irregularity over a particular track section and k is then used to predict future TQIs. However, complicated factors affect track irregularity. Roadbed state, passing tonnage, train running speed and track structure are all important factors that determine track irregularity changes. Under the joint action of various factors, changes in track irregularity are characterized by nonlinearity, which can be described the so-called Bathtub Curve. Linear prediction models provide a simple but convenient tool to predict the evolution of track irregularities. In a certain sense, these models help to deepen research and can shed new light on the pattern of track irregularity changes. However, these models inevitably have two obvious disadvantages. The first is that no systematic consideration is given to the inherent characteristics of track irregularity changes, while the second is that it is apparently impractical to use a single slope k to predict track irregularities for all track sections of a whole railway line. The result is that when linear models are used to predict track irregularity changes, big predictive errors are caused. In the light of the cyclic, exponential and multistage changes in track irregularity, the current authors have developed a multistage linear prediction model for track irregularity. Given the cyclic nature of track irregularity changes, we take a 200 m track section as the unit section for our research. Because track irregularities change at different rates within one track irregularity development cycle, we divide such changes into several shorter stages. Based on our understanding of the three major characteristics of track irregularity changes, we put forward an improved linear prediction model, namely the multistage linear prediction model (MLPM). The model adjusts the calculation method of k to make the predicted results fit better with the actually measured values. The authors finally use track car inspection data from the Beijing-Shanghai Railway Line (Jing-Hu Line) to validate the model and compare the predicted results with the measured data.

Gait in the human body measured and expressed in a biomedical signal stored in the patient's medical record. Gait is a time-series signal, depends on time changes and require a large-enough storage capacity. In this study, an optimization method based on data reduction used to compress gait data using linear prediction modeling. The estimation signal from the method decomposed using discrete wavelet transform (DWT). The estimation signal used to maintain the authenticity of the information in the gait signal. Linear modeling with order value from 8 to 11 generated similar signal with error value up to 1.67 × 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-5</sup> . Daubechies wavelet used to decompose the signal with compression level up to 25.5259%. The results of the research show that the compressed signal has a simpler data size while maintaining the value of the original data. With a smaller capacity, the designed gait database will have more efficient storage space requirements.

Development of a linear predictive model for carbon dioxide sequestration in deep saline carbonate aquifers

The ability to accurately predict an individual's risk for cancer is critical to the implementation of precision prevention measures. Current cancer risk predictions are frequently made with simple models that use a few proven risk factors, such as the Gail model for breast cancer, which are easy to interpret, but may theoretically be less accurate than advanced machine learning (ML) models. With the UK Biobank, a large prospective study, we developed models that predicted 13 cancer diagnoses within a 10-year time span. ML and linear models fit with all features, linear models fit with 10 features, and externally developed QCancer models, which are available to more than 4,000 general practices, were assessed. The average area under the receiver operator curve (AUC) of the linear models (0.722, SE = 0.015) was greater than the average AUC of the ML models (0.720, SE = 0.016) when all 931 features were used. Linear models with only 10 features generated an average AUC of 0.706 (SE 0.015), which was comparable to the complex models using all features and greater than the average AUC of the QCancer models (0.684, SE 0.021). The high performance of the 10-feature linear model may be caused by the consideration of often omitted feature types, including census records and genetic information. The high performance of the 10-feature linear models indicate that unbiased selection of diverse features, not ML models, may lead to impressively accurate predictions, possibly enabling personalized screening schedules that increase cancer survival.

Existing prediction-based works on reversible data hiding in encrypted images usually embed the secret messages by referring to the difference between current pixel and its predicted value. An accurate prediction model may promote an improvement of embedding capacity. Existing schemes, however, may not work well due to involving a bad prediction model so that their embedding capacity cannot be improved further. To address the problem, this paper proposes a new reversible data hiding scheme in encrypted images by designing double linear regression prediction model. Proposed model can significantly improve the prediction accuracy of current pixel based on neighboring pixels, more auxiliary rooms are thus vacated to embed secret data. Furthermore, a prediction error map is constructed to mark the error positions caused by inaccurate prediction, which can be further compressed lossless to lower the capacity of auxiliary data. Reversible recovery for original image can be finally achieved successfully. Experimental results demonstrate that the proposed scheme significantly improves prediction accuracy and data embedding capacity by combining double linear regression prediction model and prediction error map, and then can achieve separable and lossless recovery for the original image. Compared with existing works, the proposed scheme can implement a higher visual quality of decrypted images, while maintaining a larger embedding capacity.

This study aimed to improve the PREPARE model, an existing linear regression prediction model for long-term quality of life (QoL) of intensive care unit (ICU) survivors by incorporating additional ICU data from patients' electronic health record (EHR) and bedside monitors. The 1308 adult ICU patients, aged ≥16, admitted between July 2016 and January 2019 were included. Several regression-based machine learning models were fitted on a combination of patient-reported data and expert-selected EHR variables and bedside monitor data to predict change in QoL 1 year after ICU admission. Predictive performance was compared to a five-feature linear regression prediction model using only 24-hour data (R2 = 0.54, mean square error (MSE)=0.031, mean absolute error (MAE)=0.128). The 67.9% of the included ICU survivors was male and the median age was 65.0 [IQR: 57.0-71.0]. Median length of stay (LOS) was 1 day [IQR 1.0-2.0]. The incorporation of the additional data pertaining to the entire ICU stay did not improve the predictive performance of the original linear regression model. The best performing machine learning model used seven features (R2 = 0.52, MSE=0.032, MAE=0.125). Pre-ICU QoL, the presence of a cerebro vascular accident (CVA) upon admission and the highest temperature measured during the ICU stay were the most important contributors to predictive performance. Pre-ICU QoL's contribution to predictive performance far exceeded that of the other predictors. Pre-ICU QoL was by far the most important predictor for change in QoL 1 year after ICU admission. The incorporation of the numerous additional features pertaining to the entire ICU stay did not improve predictive performance although the patients' LOS was relatively short.

Purpose: To assess the impact of using breathing adapted radiotherapy on contralateral breast (CB) dose, to relate the thorax shape with the dose to the organs at risk (OARs) and to predict the risk for induced malignancies in CB using linear and non-linear models, following tangential irradiation of breast. Material and methods. Sixteen patients with stage I-II breast cancer treatment planned with tangential fields using deep inspiration breath hold (DIBH) and free breathing (FB) techniques were included in this analysis. The dose results mainly based on DVH analysis were compared. Four parameters were defined to describe thoracic shape. Excess relative risk (ERR) for cancer induction in CB, employing linear and non-linear models was calculated. Results. Average CB volumes exposed to a dose of 1 Gy is 1.3 times higher in DIBH plans than in FB plans. No significant difference in average V3Gy and V5Gy for DIBH and FB plans is observed. The average mean CB dose for DIBH and FB plans is 0.33 and 0.28 Gy, respectively. No correlation between thorax shape parameters and mean OARs dose is observed. The estimated average mean ERR with linear model is lower in FB plans (0.12) than for the DIBH plans (0.14). The estimated ERR with non-linear model is 0.14 for DIBH plans and 0.15 for FB plans. Conclusion. No significant difference in CB dose between DIBH and FB plans is observed. The four thorax shape parameters defined in this study can not be related to the dose at OARs using DIBH and FB radiation techniques. The ERR estimates for secondary CB cancer are nearly the same for FB and DIBH planning when using a linear and non-linear risk prediction models.

The established linear fatigue life prediction model based on the Miner rule has been widely applied to fatigue life prediction under constant amplitude uniaxial and multiaxial loading. Considering the physical significance of crack formation and propagation, a multiaxial equivalent linear fatigue life prediction model is put forward based on Miner rule and critical plane method under constant amplitude loading. The essence of this approach is that the equivalent strain, which consists of the shear strain and normal strain on the critical plane, replaces the relevant parameter of uniaxial nonlinear fatigue damage model. The principal axes of stress/strain rotate under non-proportional loading. Meanwhile, the microstructure of material and slip systems change, which lead to additional hardening effect. The ratio of cyclic yield stress to static yield stress is used to represent the cyclic hardening capacity of material, and the influence of phase difference and loading condition on the non-proportional hardening effect is considered. The multiaxial fatigue life is predicted using equivalent stain approach, maximum shear stain amplitude model, CXH model, and equivalent multiaxial liner model under proportional and/or non-proportional loading. The smooth and notched fatigue specimens of four kinds of materials (Q235B steel, titanium alloy TC4, Haynes 188, and Mod.9Cr-1Mo steel) are used in the multiaxial fatigue experiments to verify the proposed model. The predicted results of these materials are compared with the test results, and the results show that these four models can achieve good effect under proportional loading, but the proposed model performs better than the other three models under non-proportional loading. Meanwhile, it also verifies that the proposed enhancement factor can reflect the influence of phase difference and material properties on additional hardening.

The aim of the present paper is to explore and obtain a simple method capable to detect the most important variables (features) from a large set of variables. To verify the performance of the approach described in the following sections, we used a set of news. Text sources are considered high-dimensional data, where each word is treated as a single variable. In our work, a linear predictor model has been used to uncover the most influential variables, reducing strongly the dimension of the data set. Input data is classified in two categories; arranged as a collection of plain text data, pre-processed and transformed into a numerical matrix containing around 10,000 different variables. We adjust the linear model's parameters based on its prediction results, the variables with strongest effect on output survive, while those with negligible effect are removed. In order to collect, automatically, a summarized set of features, we sacrifice some details and accuracy of the prediction model, although we try to balance the squared error with the subset obtained.

This article presents experimental results of a transonic wind-tunnel test that demonstrates the use of generalized predictive control for flutter suppression for a subsonic wind-tunnel wing model. The generalized predictive control algorithm is based on the minimization of a suitable cost function over finite costing and control horizons. The cost function minimizes not only the sum of the mean square output of the plant predictions, but also the weighted square rate of change of the control input with its input constraints. An additional term was added to the cost function to compensate for dynamics of the wing model that cause it to be invariant to low input frequencies. This characteristic results in a control surface that drifts within the specified input constraints. The augmentation to the cost function that penalizes this low frequency drift is derived and demonstrated. The initial validation of the controller uses a linear plant predictor model for the computation of the control inputs. Simulation results of the closed-loop system that were used to determine nominal ranges for the tuning parameters are presented. The generalized predictive controller based on the linear predictor model successfully suppressed the flutter for all testable Mach numbers and dynamic pressures in the transonic region in both simulation and wind-tunnel testing. The results confirm that the generalized predictive controller is robust to modeling errors.

Time–frequency analysis and instantaneous frequency estimation using two-sided linear prediction

Recent text-to-video diffusion models have achieved impressive progress. In practice, users often desire the ability to control object motion and camera movement independently for customized video creation. However, current methods lack the focus on separately controlling object motion and camera movement in a decoupled manner, which limits the controllability and flexibility of text-to-video models. In this paper, we introduce Direct-a-Video, a system that allows users to independently specify motions for multiple objects as well as camera’s pan and zoom movements, as if directing a video. We propose a simple yet effective strategy for the decoupled control of object motion and camera movement. Object motion is controlled through spatial cross-attention modulation using the model’s inherent priors, requiring no additional optimization. For camera movement, we introduce new temporal cross-attention layers to interpret quantitative camera movement parameters. We further employ an augmentation-based approach to train these layers in a self-supervised manner on a small-scale dataset, eliminating the need for explicit motion annotation. Both components operate independently, allowing individual or combined control, and can generalize to open-domain scenarios. Extensive experiments demonstrate the superiority and effectiveness of our method. Project page and code are available at https://direct-a-video.github.io/.

An increase in the number of residents should be anticipated including in the health sector, especially the problem of stunting. Stunting in children disrupts height and lack of absorption of nutrients. Information and data drive change in many areas such as health, entertainment, economics, business, and other strategic areas. The stages carried out in this study are initiating, developing linear models, and making prediction results on linear machine learning models. The results of testing with the scikit-learn linear model with a minimum variable of 19 get the best test results, namely the polynomial regression with pipeline model with mean absolute percentage error (MAPE) 0.02, root mean square error (RMSE) 3.32, and coefficient of determination (R2) 1,00. Testing with the scikit-learn linear model with a maximum variable of 48 gets the best test results, namely the polynomial regression with pipeline model with MAPE 0.00, RMSE 3.79 and R2 1.00. Testing with the scikit-learn linear model with an average variable of 32 gets the best test results, namely the polynomial regression model with MAPE 0.01, RMSE 3.32, and R2 1.00. The results of testing with the scikit-learn linear model with the minimum, maximum, and average variables get the best test results, namely the polynomial regression with pipeline model.