Pattern-Based Variant-Best-Neighbors Respiratory Motion Prediction Using Orthogonal Polynomials Approximation
Authors: KinMing Kam, Shouyi Wang, Stephen Bowen, Wanpracha Chaovalitwongse
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Based on a study of respiratory motion of 27 patients with lung cancer, the proposed prediction approach generated consistently better prediction performances than the current respiratory motion prediction approaches, particularly for long prediction horizons.In our experiments, we compare the prediction performance of the proposed methods, i.e. RPKM and OPPRED, and the latest state-of-the-art methods, i.e. w LMS, SVRpred and TVSAR. In addition, Seasonal ARIMA is also added to the comparison as most people are familiar to this method. |
| Researcher Affiliation | Academia | Kin Ming Kam and Shouyi Wang Department of Industrial, Manufacturing & Systems Engineering, University of Texas at Arlington, TX 76019 Stephen R Bowen Department of Radiology and Integrated Brain Imaging Center, University of Washington, Seattle, WA 98195 Wanpracha Chaovalitwongse Department of Industrial and Systems Engineering and the Integrated Brain Imaging Center, University of Washington, Seattle, WA 98195 |
| Pseudocode | No | The paper describes its methods in text and mathematical equations but does not contain structured pseudocode or algorithm blocks (e.g., a clearly labeled "Algorithm" section or code-like formatted procedure). |
| Open Source Code | No | The paper does not provide concrete access to source code (e.g., a specific repository link, an explicit code release statement, or an indication that code is in supplementary materials) for the methodology described. |
| Open Datasets | No | Time series of abdominal displacement of 27 lung and liver cancer patients were collected with the Real-time Position Management TM(RPM)(Varian Inc., Santa Clara, CA) infrared camera and reflective marker block system during their PET/CT examination. The paper describes data collection but does not provide any specific link, DOI, repository name, or formal citation with authors/year for public access to this dataset. |
| Dataset Splits | No | before starting prediction, the first step is a training and validation process to determine the personalized pattern monitoring window length based on the statistics of the respiratory cycles of each individual patient. In validation process, one window ratio is picked each time. R-square is used for performance measurement because it provides a universal metric that describes how close the prediction is to the real data. The window ratio R that maximizes the R-square is selected for prediction. The paper describes a validation process for hyperparameter tuning, but it does not provide specific numerical dataset split information (e.g., percentages or sample counts for training, validation, and test sets). |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions methods like Neural Networks (NN), Kernel Density Estimates (KDE), Support Vector Regression Prediction (SVRpred), Recursive Least Squares (RLS), MULIN algorithms, normalized least mean squares, wavelet-based multiscale autoregression (w LMS), Wavelet Neural Network, EKF Frequency Tracking, and Seasonal ARIMA, but it does not specify any software libraries, frameworks, or programming languages with their version numbers that were used for implementation or experimentation. |
| Experiment Setup | Yes | For the experiment of RPKM and OPPRED, the personalized window size has to be determined before prediction. Also, in the experiment, the similarity threshold θ is set to be 0.95. For SVRpred, we consider 212, 211, . . . , 212 for kernel parameter, γ, and 0, 0.01, 0.02, . . . , 0.1 for insensitive zone, ϵ, and max(| y + 3σy|, | y 3σy) for regularization parameter, C. |