Boosting Technique Research Articles

Investigate the Dosimetric and Potential Clinical Benefits Utilizing Stereotactic Body Radiation Therapy With Simultaneous Integrated Boost Technique for Locally Advanced Pancreatic Cancer: A Comparison Between Photon and Proton Beam Therapy.

PurposeTo investigate the potential clinical benefits of using stereotactic body radiation therapy (SBRT) with simultaneous integrated boost (SIB) technique for locally advanced pancreatic cancer (LAPC) among different treatment modalities and planning strategies, including photon and proton.MethodA total of 19 patients were retrospectively selected in this study: 13 cases with the tumor located in the head of the pancreas and 6 cases with the tumor in the body of the pancreas. SBRT-SIB plans were generated using volumetric modulated arc therapy (VMAT), two-field Intensity Modulated Proton Therapy (IMPT), and three-field IMPT. The IMPT used the robust optimization parameters of ± 3.5% range and 5-mm setup uncertainties. Root-mean-square deviation dose (RMSD) volume histograms were used to evaluate the target coverage robustness quantitatively. Dosimetric metrics based on the dose-volume histogram (DVH), homogeneity index (HI), and normal tissue complication probability (NTCP) were analyzed to evaluate the potential clinical benefits among different planning groups.ResultsWith a similar CTV and SIB coverage, two-field IMPT provided a lower maximum dose for the stomach (median: 18.6GyE, p<0.05) and duodenum (median: 32.62GyE, p<0.05) when the target was located in the head of the pancreas compared to VMAT and three-field IMPT. The risks of gastric bleed (3.42%) and grade ≥ 3 GI toxicity (4.55%) were also decreased. However, for the target in the body of the pancreas, VMAT showed a lower maximum dose for the stomach (median 30.93GyE, p<0.05) and toxicity of gastric bleed (median: 8.67%, p<0.05) compared to two-field IMPT and three-field IMPT, while other maximum doses and NTCPs were similar. The RMSD volume histogram (RVH) analysis shows that three-field IMPT provided better robustness for targets but not for OARs. Instead, three-field IMPT increased the Dmean of organs such as the stomach, duodenum, and intestine.ConclusionThe results indicated that the tumor locations could play a critical role in determining clinical benefits among different treatment modalities. Two-field IMPT could be a better option for LAPC patients whose tumors are located in the head of the pancreas. It provides lower severe toxicity for the stomach and duodenum. Nevertheless, VMAT is preferred for the body with better protection for the possibility of gastric bleed.

Application of gradient tree boosting regressor for the prediction of scour depth around bridge piers

Abstract Scour around bridge piers is a complex phenomenon and it is essential to assess or predict the scour hazard around bridge piers in tandem with completely understanding its mechanism. To date, there is no exact method for the estimation of scour depth. Nowadays, machine learning techniques are being recognized as effective tools for the prediction of scour depth using experimental data. In the present study, gradient tree boosting (GTB) technique was used for the prediction of scour depth around various pier shapes under different streambed conditions. Sediment size, sediment quantity, velocity, and flow time were used as input parameters to predict the scour depth under clear-water and live-bed scour conditions. The scour depth was predicted for different pier shapes such as, circular, rectangular, round-nosed and sharp-nosed shaped. The GTB model predicted scour depth values were compared with that of the group method of data handling (GMDH) technique. The performance of GTB and GMDH models were then evaluated based on statistical indices such as RRMSE, NNSE, WI, MNE, SI, and KGE. The study concludes that the GTB model performance was relatively superior to that of GMDH in the prediction of scour depth around different pier shapes.

Comparison of helical tomotherapy with multi-field intensity-modulated radiotherapy treatment plans using simultaneous integrated boost in high-risk prostate cancer

Abstract Purpose: The aim of this study is to compare the dosimetric results of Helical Tomotherapy (HT) and Multi-field IMRT treatment plans using a Simultaneous Integrated Boost (SIB) technique in the treatment of High-Risk Prostate Cancer (HRPCa) with pelvic nodal radiation. Methods: Seventeen patients planned with HT and 7,8 and 9 fields IMRT were investigated. All plans were designed with the prescribed dose of 54.0 Gy to the PTVln while simultaneously delivering 74.0 Gy to the PTVPS in 30 fractions. Dosimetric data of PTV and OARs were compared. Results: HT gives a better CI and HI of PTVPS compared to multi-field IMRT plans. HT plans significantly improved target coverage (HT:0.95 vs multi-field IMRT: 0.52, 0.49 and 0.49 respectively, p &lt; 0.001). Bladder mean dose(Gy) (HT: 45.6 vs multi-field IMRT: 53.6, 53.3 and 52.7 respectively, p = 0.004) and D66%(Gy) dose (HT: 35.3 vs multi-field IMRT: 46.7, 47.0 and 44.9 respectively, p = 0.006) were lower in HT. But multi-field IMRT plans significantly reduced the rectum volume receiving more than 75 Gy; (HT V75% (%) 2.7 vs multi-field IMRT 0.8, 1.4 and 0.9 respectively, p = 0.008). HT provided better sparing of the right and left femoral head receiving a mean dose. The penile bulb and small bowel doses were the highest in HT compared with multi-field IMRT. Conclusions: HT achieved better dose distribution to target compared to multi-field IMRT. This study suggests HT as a reasonable option for the treatment of HRPCa patients.

MSQ-Index: A Succinct Index for Fast Graph Similarity Search

Graph similarity search under the graph edit distance constraint has received considerable attention in many applications, such as bioinformatics, data mining, pattern recognition and social networks. Existing methods for this problem have limited scalability because of the huge amount of memory they consume when handling very large graph databases with tens of millions of graphs. In this article, we present a succinct index that incorporates succinct data structures and hybrid encoding to achieve improved query time performance with minimal space usage. Specifically, the space usage of our index requires only 5-15 percent of the previous state-of-the-art indexing size while at the same time achieving several times acceleration in query time on the tested data. We also improve the query performance by augmenting the global filter with range searching, which allows us to perform similarity search in a reduced region. In addition, we propose two effective lower bounds together with a boosting technique to obtain the smallest possible candidate set. Extensive experiments demonstrate that our proposed approach is superior both in space and filtering to the state-of-the-art approaches. To the best of our knowledge, our index is the first in-memory index for this problem that successfully scales to cope with the large dataset of 25 million chemical structure graphs from the PubChem dataset. The source code is available online.

Dissimilarity-based boosting technique for the modelling of complex HVAC systems

The decision variables of local control loops significantly influence the overall energy use of the heating ventilation and air-conditioning (HVAC) systems. Therefore, model-based real-time optimization (MRTO) of those decision variables has been widely studied in recent years. The decision making by MRTO relies on the accuracy of the performance model used to describe the relationship between cost function and decision variables. However, due to high diversity in ambient conditions and demand load, it is very difficult to develop an accurate model of these systems without a downside. This paper presents a dissimilarity-based ensemble model of the HVAC system, which systematically ensembles two powerful modelling methods from the literature: simplified or semi-physical model; and artificial neural network model. A semi-physical model of the system was used as a generalized model to provide reliability in performance. A batch trained nonlinear-autoregressive neural network with exogenous input (NARX) was used as an artificial neural network model to provide robust and accurate performance. The ensemble technique proposed in this study is a dissimilarity-based boosting technique, i.e. able to capture the performance of the NARX model and ensure accuracy and reliability in final ensemble prediction. To evaluate its performance, it was tested for the performance prediction of a complex HVAC system under actual ambient conditions over a week and its performance was compared with both semi-physical and NARX models. It was demonstrated that the proposed dissimilarity-based ensemble model could provide improved accuracy with robust operation and reliability while maintaining reasonable computational efficiency. When compared with the semi-physical model, the proposed dissimilarity-based ensemble model provided; 60–78% reduction in prediction error in terms of normalized root-mean-square error, improvement in terms of peak signal-to-noise ratio by 55–63%, and consistent performance in terms of reduction in mean absolute percentage deviation by 51–75%.

A radiomics-based model for predicting local control of resected brain metastases receiving adjuvant SRS

PurposeAdjuvant radiosurgery to the cavities of surgically resected brain metastases provides excellent local tumor control while reducing the risk of deleterious cognitive decline associated with whole brain radiotherapy. A subset of these patients, however, will develop disease recurrence following radiosurgery. In this study, we sought to assess the predictive capability of radiomic-based models, as compared with standard clinical features, in predicting local tumor control. MethodsWe performed a retrospective chart review of patients treated with adjuvant radiosurgery for resected brain metastases at the “Institution” from 2009 to 2019. Shape, intensity and texture based radiomics features of the cavities were extracted from the pre-radiosurgery treatment planning MRI scans and trained using a gradient boosting technique with K-fold cross validation. ResultsIn total, 71 cavities from 67 treated patients were included for analysis. The 6 and 12 month local control estimates were 86% and 76%, respectively. The 6 and 12 month overall survival was 78% and 55%, respectively. Thirty-six patients developed intracranial failures outside of the surgical cavity. The predictive model for local control trained on imaging features from the whole cavity achieved an area-under-the-curve (AUC) of 0.73 on the validation set versus an AUC of 0.40 for the clinical features. ConclusionsHere we report a single institutional experience using radiomic-based predictive modeling of local tumor control following adjuvant Gamma Knife radiosurgery for resected brain metastases. We found the radiomics features to provide more robust predictive models of local control rates versus clinical features alone. Such techniques could potentially prove useful in the clinical setting and warrant further investigation.

A study on gain boosting techniques of cascode amplifier at near-fmax frequencies based on gain plane approach

A study on gain boosting techniques of cascode amplifier at near-fmax frequencies is presented in this paper. In order to intuitively analyze the effect of the gain boosting technique on the power gain of the amplifier, the gain plane approach is employed. Based on the gain plane approach, the conventional gate inductive gain boosting technique can only improve the unilateral gain (U) without improvement on the ratio of the maximum available gain (Gma) over U. A revisit on the neutralization technique, which was commonly used for the purpose of stability, is carried out. Our study reveals that the proposed bottom-over-neutralization technique can improve both U and Gma/U, thus leading to higher gain boosting. Based on the proposed technique, an amplifier is implemented in 65 nm CMOS process. The post-layout simulation results exhibit a power gain of 7.74 ​dB in 140 ​GHz, which is 5.2 ​dB higher than the traditional cascode amplifier.

AKT Inhibitors: The Road Ahead to Computational Modeling-Guided Discovery.

AKT, is a serine/threonine protein kinase comprising three isoforms—namely: AKT1, AKT2 and AKT3, whose inhibitors have been recognized as promising therapeutic targets for various human disorders, especially cancer. In this work, we report a systematic evaluation of multi-target Quantitative Structure-Activity Relationship (mt-QSAR) models to probe AKT’ inhibitory activity, based on different feature selection algorithms and machine learning tools. The best predictive linear and non-linear mt-QSAR models were found by the genetic algorithm-based linear discriminant analysis (GA-LDA) and gradient boosting (Xgboost) techniques, respectively, using a dataset containing 5523 inhibitors of the AKT isoforms assayed under various experimental conditions. The linear model highlighted the key structural attributes responsible for higher inhibitory activity whereas the non-linear model displayed an overall accuracy higher than 90%. Both these predictive models, generated through internal and external validation methods, were then used for screening the Asinex kinase inhibitor library to identify the most potential virtual hits as pan-AKT inhibitors. The virtual hits identified were then filtered by stepwise analyses based on reverse pharmacophore-mapping based prediction. Finally, results of molecular dynamics simulations were used to estimate the theoretical binding affinity of the selected virtual hits towards the three isoforms of enzyme AKT. Our computational findings thus provide important guidelines to facilitate the discovery of novel AKT inhibitors.

Machine Learning and Financial Literacy: An Exploration of Factors Influencing Financial Knowledge in Italy

In recent years, machine learning techniques have assumed an increasingly central role in many areas of research, from computer science to medicine, including finance. In the current study, we applied it to financial literacy to test its accuracy, compared to a standard parametric model, in the estimation of the main determinants of financial knowledge. Using recent data on financial literacy and inclusion among Italian adults, we empirically tested how tree-based machine learning methods, such as decision trees, random, forest and gradient boosting techniques, can be a valuable complement to standard models (generalized linear models) for the identification of the groups in the population in most need of improving their financial knowledge.

A Quadrature Digital Power Amplifier With Hybrid Doherty and Impedance Boosting for Complex Domain Power Back-Off Efficiency Enhancement

A quadrature digital power amplifier (PA) with hybrid Doherty and impedance boosting (HDIB) technique is presented for deep power back-off (PBO) efficiency enhancement in the complex domain. Less power-combining ways and dc power supplies are required for proposed PA comparing to previously reported works with deep PBO efficiency enhancement. A reconfigurable matching network (RMN) based on a novel reconfigurable transformer is proposed with more freedom to achieve a flexible load impedance tuning range of the sub-PAs. The characteristics of the reconfigurable transformer based on tunable inductors are analyzed. Efficiency enhancement is achieved at 3-/6-/9-/12-/15-dB PBOs without any supply switching or PA short-switches. The PA is fabricated in 40-nm CMOS technology with a core size of 0.83 mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> . Operating at 2.3-3.4 GHz, it introduces 24.2-dBm peak P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">out</sub> with 38.5% peak drain efficiency (DE) at 2.8 GHz. It achieves 38.5%/29.6%/18.4% at 2.8 GHz and 34.7%/26.6%/17.8% DE at 3.3 GHz for 0-/6-/12-dB PBO, 39.3%/29.5%/14.9% at 2.8 GHz, and 35.3%/27.9%/15.9% DE at 3.3 GHz for 3-/9-/15-dB PBO, respectively. For 10-MHz 256-QAM modulation signal, it delivers 16.22-/15.50-dBm average P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">out</sub> with EVM of -32.3/-33.0 dB, average DE of 24.6%/22.7%, and ACLR of -33.20/-31.54 dBc at 2.8/3.3 GHz, respectively. For 20-MHz 64 QAM modulation signal, it exhibits 16.42-/15.52-dBm average P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">out</sub> with EVM of -29.1/-29.3 dB, average DE of 24.9%/22.78%, and ACLR of -30.78/-30.74 dBc at 2.8/3.3 GHz, respectively.

Blockchain Based Trust Model Using Tendermint in Vehicular Adhoc Networks

Blockchain is the consensus-based technology used to resolve conflicts in Byzantine environments. Vehicles validate the messages received from neighboring vehicles using the gradient boosting technique (GBT). Based on the validation results, the message source vehicle generates the ratings that are to be uploaded to roadside units (RSUs), and through that, the trust offset value can be calculated. All RSUs maintain the trust blockchain, and each RSU tries to add their blocks to the trust blockchain. We proposed a blockchain-based trust management model for the vehicular adhoc network (VANET) based on Tendermint. It eliminates the problem of malicious nodes entering the network, and will also overcome the problem of power consumption. Simulation results also show that the proposed system is 7.8% and 15.6% effective and efficient in terms of packet delivery ratio (PDR) and end-to-end delay (EED), respectively, to collect the trusted data between the vehicles.

Plant Recognition Using Morphological Feature Extraction and Transfer Learning over SVM and AdaBoost

Plant species recognition from visual data has always been a challenging task for Artificial Intelligence (AI) researchers, due to a number of complications in the task, such as the enormous data to be processed due to vast number of floral species. There are many sources from a plant that can be used as feature aspects for an AI-based model, but features related to parts like leaves are considered as more significant for the task, primarily due to easy accessibility, than other parts like flowers, stems, etc. With this notion, we propose a plant species recognition model based on morphological features extracted from corresponding leaves’ images using the support vector machine (SVM) with adaptive boosting technique. This proposed framework includes the pre-processing, extraction of features and classification into one of the species. Various morphological features like centroid, major axis length, minor axis length, solidity, perimeter, and orientation are extracted from the digital images of various categories of leaves. In addition to this, transfer learning, as suggested by some previous studies, has also been used in the feature extraction process. Various classifiers like the kNN, decision trees, and multilayer perceptron (with and without AdaBoost) are employed on the opensource dataset, FLAVIA, to certify our study in its robustness, in contrast to other classifier frameworks. With this, our study also signifies the additional advantage of 10-fold cross validation over other dataset partitioning strategies, thereby achieving a precision rate of 95.85%.

Parsimonious Modelling for Estimating Hospital Cooling Demand to Improve Energy Efficiency

Abstract Of all the different types of public buildings, hospitals are the biggest energy consumers. Cooling systems for air conditioning and healthcare uses are particularly energy intensive. Forecasting hospital thermal-cooling demand is a remarkable and innovative method capable of improving the overall energy efficiency of an entire cooling system. Predictive models allow users to forecast the activity of water-cooled generators and adapt power generation to the real demand expected for the day ahead, while avoiding inefficient subcooling. In addition, the maintenance costs related to unnecessary starts and stops and power-generator breakdowns occurring over the long term can be reduced. This study is based on the operations of a real hospital facility and details the steps taken to develop an optimal and efficient model based on a genetic methodology that searches for low-complexity models through feature selection, parameter tuning and parsimonious model selection. The methodology, called GAparsimony, has been tested with neural networks, support vector machines and gradient boosting techniques. Finally, a weighted combination of the three best models was created. The new operational method employed herein can be replicated in similar buildings with similar water-cooled generators.

Reducing the burden of data collection in a fingerprinting-based VLP system using a hybrid of improved co-training semi-supervised regression and adaptive boosting algorithms

The positioning accuracy of the visible light-based fingerprinting technique depends greatly on the number of initially collected and labeled data points. The greater is the number of initial fingerprints collected, the higher is the achieved accuracy of the system. However, collecting many labeled fingerprints while simultaneously ensuring data reliability is quite time consuming. To increase the practicality and applicability of fingerprinting-based algorithms, we combine the improved co-training semi-supervised regression and adaptive boosting (Ada-XCoReg) algorithms. Ada-XCoReg is a combination of double-weighted k-nearest neighbors, cross-correlation, and an adaptive boosting technique that increases the amount of input data and enhances positioning accuracy based on randomly unlabeled data points. By applying the proposed solution to the experimental model, we proved that our approach achieved a positioning accuracy of 6.14 cm, 5.29 cm, and 2.51 cm when the numbers of initially-labeled fingerprints were 16, 25, and 49, respectively.

Modeling Diameter Distributions of Loblolly Pine Plantations in Western Gulf Coastal Plain

Abstract Diameter distribution models are useful tools for forest management planning, in particular for even-aged plantations of important commercial species such as loblolly pine. Using data collected from loblolly pine plantations across East Texas, two diameter distribution model systems were developed, with the first being a conventional, Weibull-form statistical model system and the second being developed using gradient boosting (GB) technique. Both models were tested using an independent data set and compared with the regional model currently being used, which was developed by Lee and Coble (2006). Compared with Lee and Coble (2006), the Weibull-form model of this study had 66.7% smaller prediction bias, 27.2% lower mean absolute error (MAE), and 18.9% smaller root-mean-square error (RMSE). Compared with the Weibull-form model of this study, the GB model had 33.9% lower MAE, 39.5% smaller RMSE, and greater R2. Thus, the GB model greatly outperformed the Weibull-form model, which, in turn, was greatly improved over the Lee and Coble (2006) in prediction accuracy. By combining a regional volume or weight equation, both proposed diameter distribution models can be used to predict stand wood volume or weight by diameter class. Both models, in particular the GB model, are recommended for use in predicting stand structures and developing stand and stock tables for loblolly pine plantations in the region. Study Implications Knowing future stand tree size distributions is important for forest management planning. This study developed two quantitative tools to predict diameter distributions for loblolly pine (Pinus taeda) plantations in the Western Gulf Coastal Plain, with one based on the Weibull function (Weibull-form model) and the other developed using the gradient boosting technique (GB model). For the Weibull-form model, using current stand information, readers can manually calculate future stand trees per acre by diameter class. Importantly, the Weibull-form model provides more accurate (less bias and more precise) prediction than any currently available models for loblolly pine in the region. The GB model, which uses the same predictors as the Weibull-form model, can achieve even better (similar bias but more precise) prediction than the Weibull-form model. However, no equations and model coefficients for the GB model were provided, and use of the GB model relies on computer programming. A computer program was developed to implement the GB model. We recommend use of both models, in particular of the GB model, in managing loblolly pine in the region. The results aid our understanding in loblolly pine stand structure development and management in the region.

Multi-Scale Analyses and Modeling of Metallic Nano-Layers

The current work centers on multi-scale approaches to simulate and predict metallic nano-layers’ thermomechanical responses in crystal plasticity large deformation finite element platforms. The study is divided into two major scales: nano- and homogenized levels where Cu/Nb nano-layers are designated as case studies. At the nano-scale, a size-dependent constitutive model based on entropic kinetics is developed. A deep-learning adaptive boosting technique named single layer calibration is established to acquire associated constitutive parameters through a single process applicable to a broad range of setups entirely different from those of the calibration. The model is validated through experimental data with solid agreement followed by the behavioral predictions of multiple cases regarding size, loading pattern, layer type, and geometrical combination effects for which the performances are discussed. At the homogenized scale, founded on statistical analyses of microcanonical ensembles, a homogenized crystal plasticity-based constitutive model is developed with the aim of expediting while retaining the accuracy of computational processes. Accordingly, effective constitutive functionals are realized where the associated constants are obtained via metaheuristic genetic algorithms. The model is favorably verified with nano-scale data while accelerating the computational processes by several orders of magnitude. Ultimately, a temperature-dependent homogenized constitutive model is developed where the effective constitutive functionals along with the associated constants are determined. The model is validated by experimental data with which multiple demonstrations of temperature effects are assessed and analyzed.

A CMOS implementation of controller based all digital phase locked loop (ADPLL)

PurposeBiomedical radio frequency (RF) transceivers require miniaturized forms with long battery life and low power consumption. The medical implant communication service (MICS) band in the frequency range of 402–405 MHz is widely used for medical RF transceivers because the MICS band signals have reasonable propagation characteristics and are suited to achieve good results. The implementation of the RF front-end for medical devices has many challenges as these dictate low power consumption. In particular, phase-locked loop is one of the most critical blocks of the RF front-end. The purpose of this paper is to the design of controller-based all-digital phase-locked loop (ADPLL) in a 45 nm CMOS process.Design/methodology/approachInitially, an open-loop architecture phase frequency detector (PFD) is designed. Then based on the concept of differential buffer, a differential ring oscillator (RO) is built using capacitive boosting technique. After that, the frequency controller block is built by proper mathematical modeling that does the job of loop filter, which behaves like a phase interpolator. Frequency controller block has tuning register block, tuning word register. The tuning block is built using the Metal Oxide Semiconductor (MOS) caps. Finally, the integration of all the blocks is done and the ADPLL architecture that locks at 402 MHz is achieved.FindingsThe designed PFD is dead zone free that operates at 1 GHz. The differential RO oscillates at 495 MHz. The proposed ADPLL operates at 402 MHz with measured phase noise of −98.36 at 1-MHz offset. This ADPLL exhibits rms jitter of 4.626 ps with a total power consumption of 216.5 µW.Research limitations/implicationsA time to digital converter (TDC)-less controller-based low power ADPLL covering the MICS frequency band for biomedical applications has been designed in 45 nm/0.68 V CMOS technology. The ADPLL proposed in this draft uses differential oscillator with capacitively boosted technique which reduced the operating voltage to as low as 0.68 V. This ADPLL has a bandwidth of 20 kHz and works at reference frequency of 20 MHz consumed power of 216.5 µW, while generating an output frequency of 402 MHz. The tuning range is from 375 to 428 MHz. With the phase noise of −98.36 dbc/Hz at 1 MHz, a frequency controller block replaces the usage of TDC.Social implicationsThe designed ADPLL will definitely pave way to greater research arena in the field of biomedical field. This ADPLL is a unique combination that combines electronics and biomedical field. The designed ADPLL is itself a broader application to biomedical field that will have a positive impact on the society.Originality/valueThe implementation of open-loop PFD and RO using the capacitive boosting technique is a unique combination. This is comprehended well with frequency controller block that eliminates the usage of TDC and behaves as phase interpolator. The entire design of ADPLL which suits the application of MICS band of frequency has been designed carefully to work at low power.

Data-driven framework for predicting ground temperature during ground freezing of a silty deposit

Predicting the frozen zone near the freezing pipe in artificial ground freezing (AGF) is critical in estimating the efficiency of the AGF technique. However, the complexity and uncertainty of many factors affecting the ground temperature cause difficulty in developing a reliable physical model for predicting the ground temperature. This study proposed a data-driven framework to accurately predict the ground temperature during the operation of AGF. Random forest (RF) and extreme gradient boosting (XGB) techniques were employed to develop the prediction model using the dataset of a field experiment in the silty deposit. The developed ensemble models showed relatively good performance (R2 > 0.96), yet the XGB model showed higher accuracy than the RF model. In addition, the evaluated mutual information and importance score revealed that the environmental attributes (ambient temperature, surface temperature, humidity, and wind speed) can be critical in predicting ground temperature during the AFG operation. The prediction models presented in this study can be utilized in evaluating freezing efficiency at the range of geotechnical and environmental attributes.

Performance Assessment of Ensemble Learning Model for Prediction of Cardiac Disease Among Smokers Based on HRV Features

Smoking impacts the pattern of heart rate variability (HRV); HRV therefore acts as a predictor of cardiac diseases (CD). In this study, to predict CD non-invasively among smokers, ensemble machine learning methods have been used. A single model is created based on ensemble voting classifier with a combined boosting technique to improve the accuracy of predictive model. The final ensemble model shows an accuracy of 95.20%, precision of 97.27%, sensitivity of 92.35%, specificity of 98.07%, F1 score of 0.95, AUC of 0.961, MCE of 0.0479, kappa statistics value of 0.9041, and MSE of 0.2189. The obtained accuracy by using the proposed method is the highest value achieved so far for the prediction of CD among smokers using HRV data.

Hypofractionated Radiotherapy Using Simultaneous Integrated Boost Technique with Concurrent and Adjuvant Temozolomide for Glioblastoma

Aim: This study was conducted to assess the safety and efficacy of postoperative hypofractionated radiotherapy (HRT) using simultaneous integrated boost (SIB) technique for glioblastoma (GBM) compared to conventional radiotherapy (CRT).&#x0D; Study Design: This was a prospective study with historical control arm.&#x0D; Place and Duration of the Study: Department of Clinical Oncology and Nuclear Medicine, Mansoura University Hospital, Mansoura, Egypt, between May 2017 and June 2019.&#x0D; Methods: The intervention (HRT) group included 30 patients who received 3D conformal HRT with SIB using field in field (FIF) technique to deliver a differential radiation dose to different targets. Planning target volume 60 (PTV60) includes the gross target volume (GTV) plus a 5-mm margin, and PTV45 includes the GTV plus a 15-mm margin. PTV60 will receive 60 Gy in 20 fractions, and PTV45 will receive 45 Gy in the same 20 fractions (one fraction daily and 5 days per week).The CRT group included 30 patients who received 3D conformal CRT with total dose 60 Gy in 2-Gy fractions delivered over 6 weeks. Both groups was planned to receive concurrent and adjuvant temozolamide.&#x0D; Results: The median PFS was 10 months in both groups. The median OS was 13 months in HRT group versus 12 months in CRT group which is statistically non significant. The toxicities were mild and acceptable. Performance status and adjuvant temozolamide were significant predictors that affect the overall survival.&#x0D; Conclusions: HRT with SIB using 3D conformal RTH with (FIF) technique in patients with GBM is a feasible and safe treatment and its results is comparable to the conventional radiotherapy.