Mantle cell lymphoma (MCL) in Southeast Asia specifically among Indian population presents in advanced stage with bulky disease, significant extranodal involvement, and poor ECOG PS. Indigenous ...survival prediction models for this part of the world are lacking.
Development of prediction models for overall survival (OS) and event-free survival (EFS) in Indian MCL patients.
We analyzed ambispective clinical data of 90 MCL patients treated January 2013-December 2023 at Dr. B.R. Ambedkar Institute Rotary Cancer Hospital, All India Institute of Medical Sciences (AIIMS), New Delhi, India.
Statistical analysis performed using STATA 13.0. Clinical and laboratory correlates of OS and EFS with P<.2 in univariate logistic regression analysis were included in multivariate analysis. Predictive models (AMOS and AMES scores) were developed using coefficients of variables from regression models. Receiver operating characteristic (ROC) curve analysis was used to set optimal cutoff for both models. Performance of cutoffs was reported using sensitivity, specificity. P<.05 defined statistical significance.
In multivariate analysis; age >60 years (a), presence of B symptoms (b), ECOG PS ≥2 (c), splenomegaly (d), LDH ≥ULN (e), and nonuse of rituximab maintenance (f) were significantly associated with no OS and no EFS at 1 year; male sex (g) was associated with no OS at 1 year. Each variable (a-g) was dichotomized to have a score of 0 (if variables were as mentioned above) or 1. AMOS score calculated as 18.9(a) + 20.4(b) + 10.0(c) + 11.1(d) + 19.4(e) + 33.3(f) + 14.9(g). AMES score calculated as 17.8(a) + 14.9(b) + 10.0(c) + 15.0(d) + 13.8(e) + 21.1(f). Mean (±SD) AMOS score 59.8 (±28.3); optimal cutoff at 48.8. AMOS score ≥48.8 had sensitivity, specificity of 86.0%, 81.0%, respectively, to predict OS at 1 year. Mean (±SD) AMES score 46.8 (±22.6); optimal cutoff at 42.2. AMES score ≥42.2 had sensitivity, specificity of 75.0%, 85.0%, respectively, to predict EFS at 1 year. Area under ROC (AUROC) for AMOS and AMES models were 0.86 and 0.91, respectively.
AMOS and AMES scores are indigenous models with high predictive capacity for OS and EFS, respectively, in patients of MCL from this part of the world. This exemplifies their utility to predict survival outcome in MCL patients.
Accurate traffic forecasting is critical in improving safety, stability, and efficiency of intelligent transportation systems. Despite years of studies, accurate traffic prediction still faces the ...following challenges, including modeling the dynamics of traffic data along both temporal and spatial dimensions, and capturing the periodicity and the spatial heterogeneity of traffic data, and the problem is more difficult for long-term forecast. In this paper, we propose an Attention based Spatial-Temporal Graph Neural Network (ASTGNN) for traffic forecasting. Specifically, in the temporal dimension, we design a novel self-attention mechanism that is capable of utilizing the local context, which is specialized for numerical sequence representation transformation. It enables our prediction model to capture the temporal dynamics of traffic data and to enjoy global receptive fields that is beneficial for long-term forecast. In the spatial dimension, we develop a dynamic graph convolution module, employing self-attention to capture the spatial correlations in a dynamic manner. Furthermore, we explicitly model the periodicity and capture the spatial heterogeneity through embedding modules. Experiments on five real-world traffic flow datasets demonstrate that ASTGNN outperforms the state-of-the-art baselines.
Occluded person re-identification is a challenging task as the appearance varies substantially with various obstacles, especially in the crowd scenario. To address this issue, we propose a ...Pose-guided Visible Part Matching (PVPM) method that jointly learns the discriminative features with pose-guided attention and self-mines the part visibility in an end-to-end framework. Specifically, the proposed PVPM includes two key components: 1) pose-guided attention (PGA) method for part feature pooling that exploits more discriminative local features; 2) pose-guided visibility predictor (PVP) that estimates whether a part suffers the occlusion or not. As there are no ground truth training annotations for the occluded part, we turn to utilize the characteristic of part correspondence in positive pairs and self-mining the correspondence scores via graph matching. The generated correspondence scores are then utilized as pseudo-labels for visibility predictor (PVP). Experimental results on three reported occluded benchmarks show that the proposed method achieves competitive performance to state-of-the-art methods. The source codes are available at https://github.com/hh23333/PVPM
Controlling soft robots with precision is a challenge due to the difficulty of constructing models that are amenable to model-based control design techniques. Koopman operator theory offers a way to ...construct explicit dynamical models of soft robots and to control them using established model-based control methods. This approach is data driven, yet yields an explicit control-oriented model rather than just a "black-box" input-output mapping. This work describes a Koopman-based system identification method and its application to model predictive control (MPC) design for soft robots. Three MPC controllers are developed for a pneumatic soft robot arm via the Koopman-based approach, and their performances are evaluated with respect to several real-world trajectory following tasks. In terms of average tracking error, these Koopman-based controllers are more than three times more accurate than a benchmark MPC controller based on a linear state-space model of the same system, demonstrating the utility of the Koopman approach in controlling real soft robots.
Nowadays, videos are an integral modality for information sharing on the World Wide Web. However, systems able to automatically understand the content and sentiment of a video are still in their ...infancy. Linguistic information transported in spoken parts of a video is known to convey valuable properties in regards to context and emotions. In this article, we explore a lexical knowledge-based extraction approach to obtain such understanding from the video transcriptions of a large-scale multimodal dataset (MuSe-CAR). To this end, we use SenticNet to extract natural language concepts and fine-tune several feature types on a subset of MuSe-CAR. With these features, we explore the content of a video as well as learning to predict emotional valence, arousal, and speaker topic classes. Our best model improves the linguistic baseline from the MuSe-Topic 2020 subchallenge by almost 3% (absolute) for the prediction of valence on the predefined challenge metric and outperforms a variety of baseline systems that require much higher computational power than the one proposed herein.
This article presents the application of model predictive control (MPC) in high-performance drives. A wide variety of machines have been considered: Induction machines, synchronous machines, linear ...motors, switched reluctance motors, and multiphase machines. The control of these machines has been done by introducing minor and easy-to-understand modifications to the basic predictive control concept, showing the high flexibility and simplicity of the strategy. The second part of the article is dedicated to the performance comparison of MPC with classical control techniques such as field-oriented control and direct torque control. The comparison considers the dynamic behavior of the drive and steady-state performance metrics, such as inverter losses, current distortion in the motor, and acoustic noise. The main conclusion is that MPC is very competitive concerning classic control methods by reducing the inverter losses and the current distortion with comparable acoustic noise.
The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can ...be learned with compositional subsystems. This paper models these structures by presenting PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment. Concretely, besides the original memory cell of LSTM, this network is featured by a zigzag memory flow that propagates in both bottom-up and top-down directions across all layers, enabling the learned visual dynamics at different levels of RNNs to communicate. It also leverages a memory decoupling loss to keep the memory cells from learning redundant features. We further propose a new curriculum learning strategy to force PredRNN to learn long-term dynamics from context frames, which can be generalized to most sequence-to-sequence models. We provide detailed ablation studies to verify the effectiveness of each component. Our approach is shown to obtain highly competitive results on five datasets for both action-free and action-conditioned predictive learning scenarios.
Modern military radars are sophisticated machines emitting sequences of signals for surveillance and tracking purposes. Advanced radars, known as multi-function radars (MFRs), can send out a variety ...of signals and switch between different states in a very short amount of time. To effectively jam against an MFR, the electronic warfare (EW) systems need to predict the next incoming signal and its arrival time with high accuracy. Recent years have seen an explosion of research in the application of machine learning in both radar and EW applications. This paper proposes a unified machine learning model for predicting pulse-repetition-interval (PRI) values with the next radar signal's time of arrival (TOA), as well as predicting the characteristics of the signal that the radar will emit. The simulation results demonstrate the effectiveness of the proposed method.
The parameter estimators and the disturbance observers are two widely used methods for the robustness improvement of the model predictive control schemes. This article presents a hybrid solution to ...improve the robustness of predictive torque control (PTC) for induction motor (IM) drive. A novel integral sliding mode observer (ISMO)-based ultralocal model and an adaptive observer are combined in the proposed method to establish a robust prediction model for the PTC. The stator current prediction model of the conventional PTC contains different parameters and variables of the IM that increase the sensitivity of the method. The proposed method solves this problem by replacing the conventional stator current prediction model with the ISMO-based ultralocal model, which does not require the IM's parameters. On the other hand, the stator flux prediction model of the PTC just depends on the stator resistance. So, an adaptive Luenberger observer is utilized to cancel the effect of resistance variation from the stator flux prediction model. The proposed ISMO and the Luenberger observer are constructed based on the Lyapunov theory to guarantee the stability of the proposed control method. The experimental validation of the proposed method is performed. Also, the robustness of this method has been validated experimentally.
Accurate prediction of soil thermal conductivity is crucial to the design of geothermal related structures such as ground source heat pumps (GSHPs), borehole thermal energy storage (BTES), etc. A ...critical review of soil thermal conductivity and predictive models was carried out in this study. Thirteen alternative soil thermal conductivity predictive models were reviewed and assessed with respect to the advantages, disadvantages and application conditions. Comparative model performance on sands was also conducted by predicting sand thermal conductivity and comparing with the measured values collected from literature. Linear regression analyses and root-mean square error (RMSE) analyses were performed to further evaluate the model performance. It is concluded that Zhang et al. (2015b), Chen (2008) and Haigh (2012) models are highly recommended to predict sand thermal conductivity for geothermal applications.