Multiple Trees Research Articles

Exploring the influence of tree species richness on vertical structure variability in young plantations using terrestrial laser scanning

Forest structure spatially varies at the landscape-scale (between-plot) but also local-scale (within-plot). Both scales of structural variability have significant impacts on forest ecosystem functioning and stability. However, we still have a limited understanding of how tree species richness affects the spatial structural variability. In this study, we disentangled within- and between-plot variability in stand structural variables depending on tree species richness level. Terrestrial laser scanning (TLS) technology, capable of developing forest vertical structure in 3D detail, was applied in the FORBIO tree diversity experiment at three sites in Belgium. One site was 9-year old (Hechtel-Eksel) and other two sites were 11-year old (Zedelgem and Gedinne). Each site included five different sets of one, two, three, and four tree species mixtures with one replica. At each plot, four single scan locations were used. Six stand structural variables were quantified based on TLS vertical plant profiles. We hypothesized that within-plot structural variability would increase with species richness, but that the between-plot structural variability would decrease with species richness. Our study revealed notable differences in structural variability between monocultures and mixtures across all sites examined. However, the relationship between tree species richness and structural variability patterns is site-dependent. Specifically, at the Zedelgem site, we observed increased within-plot variability and decreased between-plot variability with species richness, supporting the hypothesis that species richness drives stand structural variability. However, the hypothesized pattern was not as strong at the Hechtel-Eksel and Gedinne sites. Moreover, the various structural variables displayed contrasting responses to changes in species richness. These findings indicated the potential influence of tree species richness on within- and between-plot structural variability in young plantations, particularly in favorable site conditions with well-adapted species pools. Hence, afforestation measures would benefit from planting multiple tree species to initiate structurally complex stands by considering species richness level.

Understory vegetation diversity patterns of Platycladus orientalis and Pinus elliottii communities in Central and Southern China.

As a vital component of arbor forests, understory vegetation serves as an essential buffer zone for storing carbon due to its strong capacity for community regeneration. This study aimed to identify the diversity pattern and construction mechanism of Platycladus orientalis and Pinus elliottii understory vegetation based on large-scale sample surveys. The Bayesian Information Criterion value of species abundance distribution (SAD) indicated that the Zipf and Zipf-Mandelbrot models were the best-fitting models. The SAD and gambin fitting results suggested that the Pi. elliottii community had a more balanced structure, with most species being relatively abundant. The multiple regression tree model detected four and six indicator species in P. orientalis and Pi. elliottii communities, respectively. The α-diversity index increased with a rise in altitude and showed a wavy curve with latitude. Linear regression between the β diversity and environmental and geographic distance indicated that the P. orientalis and Pi. elliottii understory communities tended to be dominated by different ecological processes. The partition of β diversity indicated that both communities were dominated by turnover processes, which were caused by environmental classification or spatial constraints. This study helped to understand the diversity maintenance in the P. orientalis and Pi. elliottii understory vegetation communities, and will benefit for diversity restoration and conservation of pure conifer forests.

Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment

This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.

PREDICTION OF RESPONSES IN A CNC MILLING OPERATION USING RANDOM FOREST REGRESSOR

In the present-day manufacturing environment, the modeling of a machining process with the help of statistical and machine learning techniques in order to understand the material removal mechanism and study the influences of the input parameters on the responses has become essential for cost optimization and effective resource utilization. In this paper, using a past CNC face milling dataset with 27 experimental observations, a random forest (RF) regressor is employed to effectively predict the response values of the said process for given sets of input parameters. The considered milling dataset consists of four input parameters, i.e. cutting speed, feed rate, depth of cut and width of cut, and three responses, i.e. material removal rate, surface roughness and active energy consumption. The RF regressor is an ensemble learning method where multiple decision trees are combined together to provide better prediction results with minimum variance and overfitting of data. Its prediction performance is validated using five statistical metrics, i.e. mean absolute percentage error, root mean squared percentage error, root mean squared logarithmic error, correlation coefficient and root relative squared error. It is observed that the RF regressor can be deployed as an effective prediction tool with minimum feature selection for any of the machining processes.

Industrial-scale anaerobic Co-digestion (ACoD) of palm oil mill effluent (POME) and decanter cake (DC) for maximizing methane yield: An integrated machine learning and simulation-based economic analysis approach

This study employs machine learning (ML) algorithms, including multiple linear regression (MLR), decision tree (DT) and support vector regression (SVR) to predict the methane yield from the anaerobic co-digestion (ACoD) of palm oil mill effluent (POME) and decanter cake (DC) in an industry-scale anaerobic covered lagoon. Results showed that the DT model outperformed the other models with a high R2 value of 0.9763 and the lowest MAE, MSE, and RMSE values. It exhibited over 95 % similarity to the actual results, validating its effectiveness in capturing real-world scenarios. Optimisation was conducted using response surface methodology (RSM) to achieve maximum biogas production (14,245 m3/day) and methane yield (0.285 Nm3 CH4/kg CODremoved), where the optimal range of pH, organic loading rate (OLR) and dilution ratio of DC were found to be 6.83–6.94, 0.82–0.83 kg COD/m3. day and 0.09–0.11 respectively. The ACoD process was simulated, and an economic analysis was performed using SuperPro Designer v10.6. ACoD of POME and DC was more economically viable than mono-digestion of POME, with a 43.16 % improvement in return on investment (ROI), considering the trade-off between the additional cost of pre-treating DC and the additional revenue from improved biogas production using ACoD.

CROP RECOMMENDATION SYSTEM USING KNN ALGORITHM AND RANDOM FOREST

In agriculture, the integration of machine learning has been a long-standing aspiration, resulting in significant advancements. While machine learning models have been developed for crop and yield predictions, traditional algorithms like decision trees often fall short of delivering the desired accuracy. This paper introduces an accessible and user-friendly solution for crop recommendations and yield predictions. Users provide inputs such as temperature, humidity, soil pH, and rainfall. To enhance accuracy, a hybrid approach using K-nearest neighbor (KNN) and Random Forest (RF) algorithms is employed. The K-nearest neighbor (KNN) algorithm achieves an impressive accuracy rate of 98%. Additionally, the Random Forest (RF) algorithm attains a commendable 96% accuracy by aggregating multiple decision trees. These high accuracy rates signify the system's potential to empower farmers with data-driven insights for crop selection and yield projections. Furthermore, the user-friendly interface promises broader adoption within the agriculture sector, catering to users with varying levels of technical proficiency. To strengthen the system's credibility, transparency regarding data sources and quality is imperative. Utilizing accurate and relevant data for reliable predictions. In summary, this paper presents a promising solution for informed decision-making in agriculture, combining crop recommendations and yield predictions. Acknowledging the limitations of traditional approaches, it capitalizes on the strengths of K-nearest neighbor and Random Forest algorithms. Keywords: Crop recommendation, Yield prediction, Machine learning, KNN, Random Forest

Selected Leaf Diseases of Rubber: Symptoms and Control – A Review

This paper is a review article with the objective of providing valuable, recent and solid information and critical understanding of symptoms and control of selected leaf diseases of rubber tree (Hevea brasiliensis Muell. Arg) using secondary information and data harvested from previously published studies found online. Data gathered showed that H. brasiliensis is subject to a plethora of economically important diseases mainly of fungal origin, classified as leaf, stem and branch, panel and root disease. Some fundamental causal organisms of leaf diseases in H. brasiliensis includes Pseudocercospora ulei, Oidium heveae, Colletotrichum gloeosporioides and Corynespora cassiicola. Corynespora leaf fall caused by Corynespora cassiicola is currently accepted as the leaf disease which causes about 45% of yield loss to rubber in mostly Asian and African continents. The symptoms of South American Leaf Blight (SALB) range from discoloration of lamina to death of tree when untreated. Leaf disease symptoms range from white powdery patches to shriveling and falling off of tender leaves and translucent brownish yellow spots in semi-matured leaves in Oidium leaf disease. Colletotrichum leaf disease symptoms range from necrosis of tender leaves of young plants to defoliation and death of entire plant. Disease control is achieved by the use of chemicals and planting of disease-resistant varieties. Some phylloplane fungi are prospective biological control agents. The best treatment to manage Corynespora leaf fall disease (CLFD) in nurseries is the introduction of overhead shading coupled with application of the fungicide mancozeb. Diseases affecting the leaves of H. brasiliensis can be devastating and can lead to loss of multiple rubber trees and reduction in the latex production of the trees. Therefore, adequate preventive, curative and control measures against the diseases should be taking to ensure maintenance of a healthy rubber tree plantation.

T cells specific to multiple Bet v 1 peptides are highly cross-reactive toward the corresponding peptides from the homologous group of tree pollens.

Allergens from Fagales trees frequently cause spring allergy in Europe, North America, and some parts of Asia. The definition of the birch homologous group, which includes birch (Bet v), oak (Que a), alder (Aln g), hazel (Cor a), hornbeam (Car b), beech (Fag s), and chestnut (Cas s), is based on high allergen sequence identity and extensive IgE cross-reactivity. Clinical effect was seen during the alder/hazel, birch, and oak pollen seasons after treatment with tree SLIT-tablets containing only birch allergen extract. Here, we characterize T-cell reactivity with respect to epitope specificities and cross-reactivity toward various Bet v 1 family members, (PR-10/group 1 major allergens). This cross-reactivity may be part of the immunological basis of clinical effect or cross-protection when exposed to birch homologous tree species. T-cell lines were generated from 29 birch-allergic individuals through stimulation of peripheral blood mononuclear cells (PBMCs) with birch/Bet v or oak/Que a allergen extracts. T-cell responses to allergen extracts, purified group 1 allergens, and overlapping 20-mer peptides (Bet v 1, Aln g 1, Cor a 1, and Que a 1) were investigated by T-cell proliferation and cytokine production. Cross-reactivity was evaluated based on Pearson's correlations of response strength and further investigated by flow cytometry using tetramer staining for homologous peptide pairs. T-cell reactivity toward extracts and group 1 allergens from across the birch homologous group was observed for birch/Bet v as well as oak/Que a T-cell lines. T-cell lines responded to multiple Bet v 1 homologous peptides from Aln g 1 and Cor a 1 and a subset of Que a 1 peptides. Significant Pearson's correlations between frequently recognized peptides derived from Bet v 1 and the corresponding peptides derived from alder, hazel, and oak strongly supported the T-cell cross-reactivity toward these allergens. Cross-reactivity between birch and birch homologous peptides was confirmed by pMHCII tetramer staining. T cells from birch tree pollen allergic individuals respond to multiple trees within the birch homologous group in accordance with the level of sequence homology between Bet v 1 family members, (PR-10 allergens) from these allergen sources, confirming the basis for clinical cross-protection.

Advancing Cancer Document Classification with R andom Forest


 In this study, we address the challenging task of biomedical text document classification of Cancer Doc Classification, specifically focusing on lengthy research papers related to cancer. Unlike previous research that often deals with shorter abstracts and concise summaries, we curated a unique dataset comprising documents with more extensive content, each exceeding 6 pages in length. To tackle this classification challenge, we employed the Random Forest Tree method. Random Forest is a powerful ensemble learning technique that combines multiple decision trees to enhance classification accuracy and robustness. It has been widely adopted in the field of machine learning and data science for its effectiveness in handling complex classification tasks.

Diversity of Mycorrhizal fungi in Eastern Hemlock stands will significantly change with the effects of Hemlock Woolly Adelgid infestation in southwestern Nova Scotia, Canada

A foundation tree species, eastern hemlock (Tsuga canadensis) is threatened by the invasive hemlock woolly adelgid (Adelges tsugae) (HWA) in southwestern Nova Scotia, Canada. The loss of this key species and its heavily shaded ecosystems may alter the diversity of important mycorrhizal fungi in hemlock forests. Mycorrhizal fungi share a vital mutualistic relationship with their host trees; consequentially, understanding if and how the predicted eastern hemlock decline will affect mycorrhizal diversity is paramount. Using available literature, we discuss three major consequences of HWA on eastern hemlock ecosystems – changing forest composition, loss of old-growth trees, and increased insect stress on host trees – and how they will likely influence mycorrhizal communities as adelgid infestations intensify. Environmental variables are also discussed as another major influence on fungal diversity. We conclude that the mycorrhizal community of eastern hemlock forests will likely change significantly as old-growth hemlock is replaced with mixed forest. We also suggest that mycorrhizal community composition will shift in favour of generalist mycorrhizae which form symbioses with multiple tree species. These conclusions illuminate the future of hemlock forest fungi in southwestern Nova Scotia and underline the importance of conserving old-growth eastern hemlock forests and their unique fungal communities.

A Data-Driven Approach to Predict the ROP of Deep Wells in Fukang Sag

In the deep well drilling process in the Fukang Depression of the Eastern Junggar Basin, rock fracturing issues and low rate of penetration (ROP) have posed significant challenges to drilling efficiency. Accurate predictions of ROP prior to drilling are of considerable value in this context. Precise predictions enable on-site engineering teams to proactively identify drilling difficulties and anticipate potential complex scenarios, facilitating them in designing preventive measures in advance, such as selecting appropriate drill bits, adjusting drilling parameters, or employing specific drilling techniques to address these issues. This, in turn, enhances drilling efficiency and greatly reduces drilling risks. Traditional mechanical-specific energy drilling rate models, despite their widespread use, exhibit significant disparities with actual results when predicting ROP. These models only consider the influence of drill bits, drilling tools, and some drilling parameters on ROP, failing to adequately account for the variations caused by engineering factors and failing to capture the interrelationships between various parameters, especially when dealing with complex subsurface formations in the Fukang Depression. Random forest is a non-parametric algorithm in the field of machine learning that is suitable for analyzing and predicting ROP affected by various complex and non-linear drilling parameters. This paper establishes a Random forest model based on a dataset containing multiple variables of logging parameters and the actual ROP. The model ranks and assesses the important feature parameters of ROP to reveal their impact. Additionally, the model uses bootstrap sampling and feature random selection to construct multiple decision trees, reducing the risk of overfitting and endowing the model with a high generalization capability. Evaluation metrics indicate that the model exhibits a high prediction accuracy and performs well, significantly improving the accuracy of mechanical drilling rate predictions in the deep wells of the Fukang Depression. This model provides robust support and serves as a positive demonstration for addressing mechanical drilling rate issues in complex subsurface formations in the future.

Multi-UAV Urban Logistics Task Allocation Method Based on MCTS

Unmanned aerial vehicles (UAVs) open new methods for efficient and rapid transportation in urban logistics distribution, where task allocation is a significant issue. In urban logistics systems, the energy status of UAVs is a critical factor in ensuring mission fulfillment. While extensive literature addresses the energy consumption of UAVs during tasks, the feasibility of energy replenishment must be addressed, which introduces additional uncertainty to the task allocation. This paper realizes multi-tasking, considering the energy consumption and replenishment of UAVs, to ensure that the tasks can be accomplished while reducing energy consumption. This paper proposes uniform distribution K-means to realize balanced multi-task grouping. Based on the Monte Carlo tree search (MCTS), a task-allocation-oriented MCTS method is proposed, including improving the selection and simulation process of MCTS. The aim was to collaborate with multiple trees for node selection and record historical simulation information to guide subsequent simulations for better results. Finally, the optimality of the proposed method was validated by comparing it with other relevant MCTS methods through several randomized experiments.

The Performance of Discriminative Tracking Algorithms for the Sway Frequency Measurement of Betula platyphylla Sukaczev (Individual Branch and Tree) under Artificial and Natural Excitation

The sway frequency is an important component of the dynamic characteristics of trees. Video-based methods can be used to measure the sway frequencies of trees. The key to successfully measuring tree sway frequency using video methods lies in whether the tracking method employed is appropriate. Based on six algorithms, i.e., Boosting, TLD, MIL, KCF, MOSSE and CSR-DCF, the tracking performance and accuracy of tree sway frequency measurements were investigated under two conditions: artificial excitation and environmental excitation. The results show that the following: (1) In terms of the tracking speed of tree sway, MOSSE > KCF > CSR-DCF > Boosting > MIL > TLD. (2) The TLD algorithm is not suitable for tree sway tracking. Boosting, MIL, MOSSE, KCF and CSR-DCF can be used for tree sway tracking. (3) Boosting, MIL and MOSSE are suitable for measuring the sway frequency of artificially excited branches and environmentally excited trees. (4) KCF and CSR-DCF algorithms are not suitable for the measurement of branch sway frequency under artificial excitation conditions but can be used for the measurement of tree sway frequency under environmental excitation conditions. However, it should be noted that this experiment only takes a Betula platyphylla Sukaczev tree and a Betula platyphylla Sukaczev branch as the research object to verify the effectiveness and feasibility of each tracking method, and does not verify the generalization ability of the above methods (on multiple tree species and multiple trees).

Physics-informed machine learning prediction of the martensitic transformation temperature for the design of “NiTi-like” high entropy shape memory alloys

The present study proposes a physics-informed machine learning (PIML) algorithm-based approach aimed at predicting the martensitic transformation temperature (Ms) for the design of “NiTi-like” high entropy shape memory alloys (HESMAs). A previously established HESMAs database is enriched and extended to include binary, ternary, quaternary, quinary and senary alloys containing the most employed alloying elements for HEAs design such as Ni equivalents (Fe, Cu, Co, Pd, Pt and Au), Ti equivalents (Zr and Hf), Nb and Ta. The Extremely Randomized Trees algorithm, based on the concept of multiple random decision tree predictions, is adopted as the regression method for Ms temperature prediction. Two strategies for the algorithm inputs have been adopted, discussed, and compared in terms of reliable predictions. The first relies on the composition of the alloying elements, whereas the second exploits a defined set of intrinsic material descriptors. The latter are based on mixing enthalpy, atomic radius, electronegativity, atomic number and number of elements. A high accuracy of the MS prediction has been reached when considering the material descriptors. In fact, the second strategy induces a mean absolute error that is less than 30 °C for alloys containing up to 4 elements. For more elements there are more discrepancies due to the homogenization state required for HEAs. The validation of the developed approach has been performed using 6 home-made HESMAs prepared specifically for this study. It demonstrated the predictive capabilities of the developed physics-informed machine learning based approach. Finally, a HESMA design tool has been implemented to virtually design new HESMAs with a targeted Ms temperature above 400 °C. It is worth noting that this aspect is one of the most challenging engineering issues for such alloys. An illustrative case applied to the (NiCuPd)50(TiZr)50 family of alloys demonstrates the predictive capabilities of the developed approach to design such alloys to achieve a Ms temperature in the range of 300 °C to 700 °C.

Improved RRT global path planning algorithm based on Bridge Test

The RRT algorithm based on random sampling is widely used in planning problems with non-holonomic constraints. In indoor environments, narrow passages exist in the map, and the RRT method suffers from slow convergence speed and poor path quality. Additionally, the typical feature of large indoor room spaces with small exits creates traps where RRT can easily become stuck, making it difficult to find a path quickly. To solve the above problems, this paper proposes an improved RRT algorithm. This method first uses the simplified Bridge Test and point cloud clustering algorithm to locate the narrow passages on the map and place the root nodes in the narrow passage. Then grow multiple random trees from the root nodes, starting and endpoints. As the number of samples increases, the random trees gradually expand and connect to each other. The trees are connected to each other to build a complete path. Finally, the initial path is optimized and the final planning result is obtained. The simulation of the improved RRT, RRT*, RRT, and Bi-RRT is carried out. The simulation results show that the improved RRT algorithm proposed in this paper outperforms in terms of path length, number of exploring nodes, and processing time. We also tested 4 algorithms on a real robot, and the results prove the practical value of the improved algorithm.

A Novel Machine-Learning Model to Predict Early Relapse in Mantle Cell Lymphoma (MCL)

Background MCL is currently an incurable disease. Although survival has greatly improved due to the advent of more effective treatments, early relapse or refractoriness after the first-line treatment (1L) is independently associated with a dismal outcome (Visco et al, BJH 2019). An early identification of these higher-risk patients would allow to optimize their management strategies and, possibly, to improve their outcome. The purpose of this study was to develop a novel prognostic model index that could predict, from the time of diagnosis, the risk of early relapse. Methods Patients diagnosed with MCL from 6 Spanish centers between January 2000 and December 2021 and treated with ≥1 lines were retrospectively analyzed (training population). An external cohort from an additional Spanish hospital was used to further validate the score (test cohort). Patients were classified as early-POD (E-POD: refractory to 1L or relapsing ≤24 m from diagnosis) or late-POD (L-POD: relapse after 1L beyond 24 m from diagnosis or absence of relapse at data cut-off). All patients had a follow-up (FU) ≥24 m from diagnosis to be evaluable for POD24, except those dying from MCL <24m, who were included as E-POD. The LASSO method with the minimum lambda was used to identify the most relevant variables affecting POD24. Missing variables in the training cohort were imputed so as not to lose patients. To enhance the predictive performance, a multimodal approach was adopted. First, a random forest survival (RFS) model was constructed using the variables selected by LASSO to predict Overall Survival (OS). Subsequently, a gradient-boosting (GB) model was developed to predict POD24, incorporating both the LASSO-selected variables and the risk predictions derived from the RFS model. Results The training cohort included 231 patients, 99 (43%) E-POD and 132 (57%) L-POD, and the test cohort 38 patients, 12 (32%) E-POD and 26 (68%) L-POD. Table 1 shows the baseline characteristics of both cohorts. Median FU was 97.12 m (86.93 -113.45) for the training cohort and 120.44 m (103.69 -144.82) for the test cohort. Among the variables associated with the risk of E-POD in the univariate analysis (age>65 years, no previous transplant, advanced stage, high-risk MIPI, Ki67≥30% and blastoid morphology), the LASSO method selected a total of 4: age at diagnosis, stage (I-II vs. III-IV), MIPI group (low, intermediate or high risk) and morphologic variant (classic vs. blastoid/pleomorphic). These variables, adjusted for POD24 as the endpoint, were first included in the RFS model to estimate the OS of each patient, obtaining a c-index of 0.78 in both the training and the validation cohorts. Then, we performed a GB model to predict the risk of E-POD, by including the same LASSO-selected variables in addition to the risk prediction of survival obtained with the RFS model, with relative weights of 9.86% (age), 0.38% (stage), 14.34% (MIPI), 16.18% (morphology) and 59.25% (estimated OS). The resulting model showed an AUC (area under the curve) of 0.82 and 0.75 in the training and test cohorts, respectively, and the calibration curves for the prediction model in both cohorts are shown in Figure 1. Our model identifies 3 tertile groups with differentiated risk of E-POD: high, intermediate and low risk with an accuracy of 81% and 74%, sensitivity 81% and 70%, specificity 81% and 76%, positive predictive value 78% and 64% and negative predictive value 85% and 81% for the training and validation cohorts, respectively. Since Gradient Boosting models are an ensemble of multiple decision trees and their predictions are made by combining the outputs of these trees using weighted averaging, rather than using a fixed mathematical formula with coefficients as in traditional linear models, a formula cannot be provided. Therefore, an online application is currently under construction to make the calculation of this E-POD index score widely applicable. Conclusion This new index score can predict the risk of E-POD at diagnosis, allowing for an earlier identification of this high-risk patient subset in need of more effective treatment strategies. External validation of this E-POD index score in a larger cohort is warranted to allow a wider application of this prognostic tool.

Multi-Level Factors Underlying Racial/Ethnic Inequities in Clinical Trial Participation Among Patients with Hematologic Cancers: Lessons for the Development of Diversity Plans

Background: The US Food & Drug Administration announced that drug sponsors will be required to implement plans to improve racial/ethnic diversity in clinical trials starting in 2024. While historically marginalized racial/ethnic populations are less likely to participate in cancer trials, there is limited information regarding inequities in access to hematologic cancer trials. It is also unknown whether social determinants of health (SDOH) explain racial/ethnic inequities in trial participation. Here we examined the extent to which commonly used trial inclusion criteria and SDOH factors explain racial/ethnic inequities in clinical trial participation among patients with six hematologic cancers. Methods: This retrospective study used the nationwide Flatiron Health electronic health record-derived de-identified database (2011-2022) of adult patients with multiple myeloma, non-Hodgkin's lymphoma (diffuse large B-cell, follicular, or mantle cell lymphoma) or leukemia (chronic lymphocytic or acute myeloid leukemia). Area-level SDOH ( e.g. predominant race/ethnicity - a measure of segregation) characterizing where patients lived were assessed using the American Community Survey census tract data. Patients were followed from initial diagnosis to clinical study drug receipt (a proxy for trial participation), death, or last recorded activity. Associations of race/ethnicity and SDOH factors with trial participation were assessed using cause-specific hazards models adjusted for clinical confounders (diagnosis year, age, sex, and cancer type). To determine which commonly used trial inclusion criteria ( i.e. abnormal creatinine serum [≥ 2] and performance status) and SDOH factors underlie racial/ethnic inequities, mediation analysis was performed using nonlinear multiple additive regression tree models. Results: This study included 51,382 patients (median age: 67 years, 42.2% women; 57.7% non-Latinx [NL] White, 6.9% NL Black, 6.1% Latinx, 29.4% other/unknown). Black and Latinx patients were more likely to live in marginalized areas ( e.g. segregated neighborhoods color and higher percentages of limited English proficiency and low vehicle ownership) than White patients. Overall, 5.6% of patients participated in trials. Patients who received care from community practices or lived in marginalized neighborhoods were less likely to participate in trials. Black (4.2%; hazard ratio [HR] 0.62, 95% confidence interval [CI]: 0.52- 0.73) and Latinx patients (3.7%; HR 0.53, CI: 0.44-0.65) were less likely to participate in trials than White patients (6.4%). Black-White trial inequities were mediated (77%, CI: 42%-117%) by practice type ( e.g., community vs. academic center, 19%, CI: 9%-28%) and area-level SDOH such as segregation (49%, CI: 21%-77%) and vehicle ownership (12%, CI: 1%-24%). Mediators explained 55% (CI: 23%-87%) of the Latinx-White trial participation inequity; area-level SDOH-including segregation (30%, CI: 3%-58%), limited English proficiency (21%, CI: -3% to 45%), and vehicle ownership (17%, CI: 0%-45%)-were the most important mediators. Clinical factors did not substantially mediate racial/ethnic inequities (< 3% proportion mediated). Conclusion: Black and Latinx patients diagnosed with hematologic cancers are 40% to 50% less likely to participate in clinical trials than their White counterparts. SDOH factors explained most of these inequities. These findings suggest that efforts to increase racial/ethnic diversity in cancer trials must address the persistent effects of segregation, along with everyday obstacles to clinical care, such as transportation and language barriers. Without concerted efforts to increase trial participation among historically marginalized racial/ethnic groups, trials may perpetuate inequities in investigational drug access and adversely impact the generalizability of pivotal cancer treatment trials.

Container Power Consumption Prediction Based on GBRT-PL for Edge Servers in Smart City

Edge computing and IoT devices have been widely deployed in smart city applications due to the rapid promotion and implementation of 5G communication technology. Limited by power supply and hardware computing capability, applications on edge servers are mostly deployed and run in the form of container micro-services to improve resource utilization. Therefore, identifying the power consumption at the container granularity is of great importance for the load scheduling and service quality assurance of edge servers. In this paper, a GBRT-PL-based container power prediction method is proposed. Performance metrics with a strong correlation between container and server power consumption are selected for power consumption modeling. To effectively suit the nonlinear relationship between container performance metrics and server power consumption, the integrated predictive capabilities of multiple regression trees and the segmented linear model of single regression tree leaf nodes are applied. The data from the experiments prove that the GBRT-PL model predicts power consumption more accurately than other models for single and multiple container groups. The highest average relative error rate in the four multi-container group tests is 6.72%, whereas the highest relative error rate in the 90% quantile is 11.66%. In addition, it can accurately predict the majority of power consumption peaks, which contributes to the precise detection of power consumption anomalies.

Automatic construction of classification dimensions by clustering texts based on common words

A way to efficiently manage large sets of texts is to construct multiple dimensions on texts and manage the texts from the dimensions. The key problem is to use a suitable representation model of text to classify texts into class trees representing dimensions. Traditional vector-based distance definitions are unsuitable to restrict the semantic relations between texts and measure the similarity of a set of more than two texts. Frequently occurred common words within a set of texts represent the texts but traditional frequent-term-set based text clustering approaches and the topic model are unsuitable for generating class trees on texts. This paper proposes an approach to using common words to represent texts and measuring the similarity of a class of texts by calculating the sum of the weights of common words of the class that indicate the common semantics of these texts. The idea is in line with the characteristics of human classification of texts. A bottom-up text clustering approach is proposed to construct class trees of texts. The common words of each class on the class trees are used as the label of the class to indicate the common semantics of the class and manage the texts of the class. Therefore, the approach can be used to construct multiple classification trees on texts. The experiments for evaluating the classification accuracy and the structure of the constructed class trees show that our approach is better than other clustering algorithms. A document summarization approach based on our approach reaches a good performance.

A Consolidated Tree Structure Combining Multiple Regression Trees With Varying Depths, Resulting in an Efficient Ensemble Model

A Consolidated Tree Structure Combining Multiple Regression Trees With Varying Depths, Resulting in an Efficient Ensemble Model