High Imbalance Research Articles

Using the MSFNet Model to Explore the Temporal and Spatial Evolution of Crop Planting Area and Increase Its Contribution to the Application of UAV Remote Sensing

Remote sensing technology can be used to monitor changes in crop planting areas to guide agricultural production management and help achieve regional carbon neutrality. Agricultural UAV remote sensing technology is efficient, accurate, and flexible, which can quickly collect and transmit high-resolution data in real time to help precision agriculture management. It is widely used in crop monitoring, yield prediction, and irrigation management. However, the application of remote sensing technology faces challenges such as a high imbalance of land cover types, scarcity of labeled samples, and complex and changeable coverage types of long-term remote sensing images, which have brought great limitations to the monitoring of cultivated land cover changes. In order to solve the abovementioned problems, this paper proposed a multi-scale fusion network (MSFNet) model based on multi-scale input and feature fusion based on cultivated land time series images, and further combined MSFNet and Model Diagnostic Meta Learning (MAML) methods, using particle swarm optimization (PSO) to optimize the parameters of the neural network. The proposed method is applied to remote sensing of crops and tomatoes. The experimental results showed that the average accuracy, F1-score, and average IoU of the MSFNet model optimized by PSO + MAML (PSML) were 94.902%, 91.901%, and 90.557%, respectively. Compared with other schemes such as U-Net, PSPNet, and DeepLabv3+, this method has a better effect in solving the problem of complex ground objects and the scarcity of remote sensing image samples and provides technical support for the application of subsequent agricultural UAV remote sensing technology. The study found that the change in different crop planting areas was closely related to different climatic conditions and regional policies, which helps to guide the management of cultivated land use and provides technical support for the realization of regional carbon neutrality.

PCFS: An intelligent imbalanced classification scheme with noisy samples

Imbalanced classification is an important research direction in machine learning. In this field, imbalanced data with noise is a challenging problem. Although many methods have been proposed to solve it, the problem remains open. If there is a method by which the information of noise and normal samples can be properly expressed at the same time, good results will be achieved. Therefore, this paper proposes the Polynomial Curve Fitting Sampling scheme, called PCFS, which uses random partition vectors and danger samples to obtain the characteristics of samples and noise respectively. The polynomial is then used to curve fit these data and fuse their features, and then adjusted the boundary between the majority and minority classes of the imbalanced datasets. After undersampling, ensemble learning is used for further improvement. Compared with the seven state-of-the-art algorithms on 15 imbalanced datasets, the effect of the proposed method is more excellent. In particular, it has obvious advantages in high noise and high imbalance rate datasets. Also, PCFS has been applied to the recognition of electric larceny in power industry and achieved good results. This shows that our method has a bright future in dealing with practical problems of complex imbalances. The implementation of the proposed PCFS in programming language Python is available at https://github.com/a2nie/PCFS.

Sparse deep encoded features with enhanced sinogramic red deer optimization for fault inspection in wafer maps

AbstractDue to the complexity and dynamics of the semiconductor manufacturing processes, wafer bin maps (WBM) present various defect patterns caused by various process faults. The defect type detection on wafer maps provides information about the process and equipment in which the defect occurred. Recently, automatic inspection has played a vital role in meeting the high-throughput demand, especially with deep convolutional neural networks (DCNN) which shows promising efficiency. At the same time, the need for a large amount of labeled and balanced datasets limits the performance of such approaches. In addition, complex DCNN in recognition tasks can provide redundant features that cause overfitting and reduce interpretability. In this paper, a new hybrid deep model for wafer map fault detection to get over these challenges is proposed. Firstly, a new convolutional autoencoder (CAE) is employed as a synthetization model to fix the high imbalance problem of the dataset. Secondly, for efficient dimensionality reduction, an embedding procedure is applied to the synthesized maps to get sparse encoded wafer maps by reinforcing a sparsity regularization in an encoder-decoder network to form a sparsity-boosted autoencoder (SBAE). The sparse embedding of wafer maps guarantees more discriminative features with 50% reduction in spatial size compared to the original wafer maps. Then, the 2D encoded sparse maps are converted to 1D sinograms to be fed later into another aggressive feature reduction stage using a new modified red deer algorithm with a new tinkering strategy. The resultant feature pool is reduced to ~ 25 1D feature bases, i.e., ~ 1.5% of the initial size of the 2D wafer maps. Finally, for the prediction stage, a simple 1DCNN model is introduced. The proposed inspection model is tested via different experiments on real-world wafer map dataset (WM-811K). Compared to state-of-the-art techniques, the proposed model outperforms their performance even with small-sized 1D feature pool. The average testing accuracy are 98.77% and 98.8% for 9 and 8 types of faults, respectively.

Computational evaluation of PEMFC performance based on bipolar plate material types

Materials used in bipolar plates are essential for addressing the challenges associated with the large-scale commercialization of Proton Exchange Membrane Fuel Cells (PEMFCs). Therefore, it is necessary to develop effective performance evaluation approaches to evaluate the performance of materials. This work has presented a high-fidelity mathematical model that includes electrochemical, fluid flow, energy, species transport, water formation, and transport aspects to simulate the conditions in a PEMFC system and to theoretically assess the performances of commercial bipolar plate materials. Accordingly, the effects of metallic (aluminum) and carbon-based (graphite and graphite composite) bipolar plate materials on the current collection performance, thermal management, water management, and overall efficiency of PEMFCs are analyzed. The findings suggest that the current density, power density, and operating voltage of each PEMFC are greatly affected by the bipolar plate material used. When compared to graphite bipolar plates, the aluminum and graphite composite bipolar plates have exhibited 16.5 % and 7.5 % higher power densities, respectively. The change in operating conditions and thermal environments caused by a change of bipolar plate materials gives rise to distinct water transport phenomena according to their respective capabilities in the balancing of liquid water movements across the membrane, which in turn affects the species distribution pattern. Specifically, the high imbalance between the electro-osmotic drag and back diffusion in the case of aluminum bipolar plate leads to a severe membrane dry-out on the anode side, limiting the hydrogen concentration in the region.

Dense center-direction regression for object counting and localization with point supervision

Object counting and localization problems are commonly addressed with point-supervised learning, which allows the use of less labor-intensive point annotations. However, learning based on point annotations poses challenges due to the high imbalance between the sets of annotated and unannotated pixels, which is often treated with Gaussian smoothing of point annotations and focal loss. However, these approaches still focus on the pixels in the immediate vicinity of the point annotations and exploit the rest of the data only indirectly. In this work, we propose a novel approach termed CeDiRNet for point-supervised learning that uses a dense regression of directions pointing towards the nearest object centers, i.e. center-directions. This provides greater support for each center point arising from many surrounding pixels pointing towards the object center. We propose a formulation of center-directions that allows the problem to be split into the domain-specific dense regression of center-directions and the final localization task based on a small, lightweight, and domain-agnostic localization network that can be trained with synthetic data completely independent of the target domain. We demonstrate the performance of the proposed method on six different datasets for object counting and localization and show that it outperforms the existing state-of-the-art methods. The code is accessible on GitHub at https://github.com/vicoslab/CeDiRNet.git.

A multi-season machine learning approach to examine the training load and injury relationship in professional soccer

OBJECTIVES: The purpose of this study was to use machine learning to examine the relationship between training load and soccer injury with a multi-season dataset from one English Premier League club. METHODS: Participants were 35 male professional soccer players (aged 25.79±3.75 years, range 18–37 years; height 1.80±0.07 m, range 1.63–1.95 m; weight 80.70±6.78 kg, range 66.03–93.70 kg), with data collected from the 2014–2015 season until the 2018–2019 season. A total of 106 training loads variables (40 GPS data, 6 personal information, 14 physical data, 4 psychological data and 14 ACWR, 14 MSWR and 14 EWMA data) were examined in relation to 133 non-contact injuries, with a high imbalance ratio of 0.013. RESULTS: XGBoost and Artificial Neural Network were implemented to train the machine learning models using four and a half seasons’ data, with the developed models subsequently tested on the following half season’s data. During the first four and a half seasons, there were 341 injuries; during the next half season there were 37 injuries. To interpret and visualize the output of each model and the contribution of each feature (i.e., training load) towards the model, we used the Shapley Additive Explanations (SHAP) approach. Of 37 injuries, XGBoost correctly predicted 26 injuries, with recall and precision of 73% and 10% respectively. Artificial Neural Network correctly predicted 28 injuries, with recall and precision of 77% and 13% respectively. In the model using Artificial Neural Network (the relatively more accurate model), last injury area and weight appeared to be the most important features contributing to the prediction of injury. CONCLUSIONS: This was the first study of its kind to use Artificial Neural Network and a multi-season dataset for injury prediction. Our results demonstrate the potential to predict injuries with high recall, thereby identifying most of the injury cases, albeit, due to high class imbalance, precision suffered. This approach to using machine learning provides potentially valuable insights for soccer organizations and practitioners when monitoring load injuries.

A detailed study of resampling algorithms for cyberattack classification in engineering applications.

The evolution of engineering applications is highly relevant in the context of protecting industrial systems. As industries are increasingly interconnected, the need for robust cybersecurity measures becomes paramount. Engineering informatics not only provides tools for knowledge representation and extraction but also affords a comprehensive spectrum of developing sophisticated cybersecurity solutions. However, safeguarding industrial systems poses a unique challenge due to the inherent heterogeneity of data within these environments. Together with this problem, it's crucial to acknowledge that datasets that simulate real cyberattacks within these diverse environments exhibit a high imbalance, often skewed towards certain types of traffics. This study proposes a system for addressing class imbalance in cybersecurity. To do this, three oversampling (SMOTE, Borderline1-SMOTE, and ADASYN) and five undersampling (random undersampling, cluster centroids, NearMiss, repeated edited nearest neighbor, and Tomek Links) methods are tested. Particularly, these balancing algorithms are used to generate one-vs-rest binary models and to develop a two-stage classification system. By doing so, this study aims to enhance the efficacy of cybersecurity measures ensuring a more comprehensive understanding and defense against the diverse range of threats encountered in industrial environments. Experimental results demonstrates the effectiveness of proposed system for cyberattack detection and classification among nine widely known cyberattacks.

TD²-Net: Toward Denoising and Debiasing for Video Scene Graph Generation

Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might contain occluded and blurred objects. 2) Label bias, primarily due to the high imbalance between a few positive relationship samples and numerous negative ones. Additionally, the distribution of relationships exhibits a long-tailed pattern. To address the above problems, in this paper, we introduce a network named TD2-Net that aims at denoising and debiasing for dynamic SGG. Specifically, we first propose a denoising spatio-temporal transformer module that enhances object representation with robust contextual information. This is achieved by designing a differentiable Top-K object selector that utilizes the gumbel-softmax sampling strategy to select the relevant neighborhood for each object. Second, we introduce an asymmetrical reweighting loss to relieve the issue of label bias. This loss function integrates asymmetry focusing factors and the volume of samples to adjust the weights assigned to individual samples. Systematic experimental results demonstrate the superiority of our proposed TD2-Net over existing state-of-the-art approaches on Action Genome databases. In more detail, TD2-Net outperforms the second-best competitors by 12.7% on mean-Recall@10 for predicate classification.

CDSKNNXMBD: a novel clustering framework for large-scale single-cell data based on a stable graph structure

BackgroundAccurate and efficient cell grouping is essential for analyzing single-cell transcriptome sequencing (scRNA-seq) data. However, the existing clustering techniques often struggle to provide timely and accurate cell type groupings when dealing with datasets with large-scale or imbalanced cell types. Therefore, there is a need for improved methods that can handle the increasing size of scRNA-seq datasets while maintaining high accuracy and efficiency.MethodsWe propose CDSKNNXMBD (Community Detection based on a Stable K-Nearest Neighbor Graph Structure), a novel single-cell clustering framework integrating partition clustering algorithm and community detection algorithm, which achieves accurate and fast cell type grouping by finding a stable graph structure.ResultsWe evaluated the effectiveness of our approach by analyzing 15 tissues from the human fetal atlas. Compared to existing methods, CDSKNN effectively counteracts the high imbalance in single-cell data, enabling effective clustering. Furthermore, we conducted comparisons across multiple single-cell datasets from different studies and sequencing techniques. CDSKNN is of high applicability and robustness, and capable of balancing the complexities of across diverse types of data. Most importantly, CDSKNN exhibits higher operational efficiency on datasets at the million-cell scale, requiring an average of only 6.33 min for clustering 1.46 million single cells, saving 33.3% to 99% of running time compared to those of existing methods.ConclusionsThe CDSKNN is a flexible, resilient, and promising clustering tool that is particularly suitable for clustering imbalanced data and demonstrates high efficiency on large-scale scRNA-seq datasets.

High imbalance fault diagnosis of aviation hydraulic pump based on data augmentation via local wavelet similarity fusion

Data augmentation methods, such as SMOTE and deep generative networks, have the potential to solve class-imbalance issue in aviation hydraulic pump fault diagnosis. Nevertheless, the scarcity of faulty samples often leads augmented samples generated using such methods suffer from blurred category boundaries, limited diversity, and mode collapse. To avoid these issues, a new data augmentation method namely Local Wavelet Similarity Fusion (LWSF) is proposed, which augments faulty samples by preserving and distorting the wavelet packet coefficients (WPCs) of the original faulty samples. An important property is that LWSF can generate high-quality synthesis samples without complex model training. First, faulty samples are decomposed into a series of frequency bands using wavelet packet decomposition. Second, the amplitudes of WPCs at a few randomly selected frequency bands are distorted, which is accomplished through a similarity-weighted fusion of the target WPCs with the closest related WPCs matched from reference samples, with the goal of keeping distortion within an appropriate range. Third, these WPCs are used to reconstruct the samples, which serve as the augmented samples. Besides, to enhance diversity, normal samples are also employed to assist in the distortion. Finally, the effectiveness of LWSF is validated by a series of experimental comparisons. In an imbalanced fault diagnosis task, the accuracy and F1-score obtained by LWSF are 97.16 % and 97.35 %, respectively, which are 3.59 % and 7.30 % higher than the best one among the five compared methods.

Addressing data imbalance in Sim2Real: ImbalSim2Real scheme and its application in finger joint stiffness self-sensing for soft robot-assisted rehabilitation.

The simulation-to-reality (sim2real) problem is a common issue when deploying simulation-trained models to real-world scenarios, especially given the extremely high imbalance between simulation and real-world data (scarce real-world data). Although the cycle-consistent generative adversarial network (CycleGAN) has demonstrated promise in addressing some sim2real issues, it encounters limitations in situations of data imbalance due to the lower capacity of the discriminator and the indeterminacy of learned sim2real mapping. To overcome such problems, we proposed the imbalanced Sim2Real scheme (ImbalSim2Real). Differing from CycleGAN, the ImbalSim2Real scheme segments the dataset into paired and unpaired data for two-fold training. The unpaired data incorporated discriminator-enhanced samples to further squash the solution space of the discriminator, for enhancing the discriminator's ability. For paired data, a term targeted regression loss was integrated to ensure specific and quantitative mapping and further minimize the solution space of the generator. The ImbalSim2Real scheme was validated through numerical experiments, demonstrating its superiority over conventional sim2real methods. In addition, as an application of the proposed ImbalSim2Real scheme, we designed a finger joint stiffness self-sensing framework, where the validation loss for estimating real-world finger joint stiffness was reduced by roughly 41% compared to the supervised learning method that was trained with scarce real-world data and by 56% relative to the CycleGAN trained with the imbalanced dataset. Our proposed scheme and framework have potential applicability to bio-signal estimation when facing an imbalanced sim2real problem.

Commit-time defect prediction using one-class classification

Existing Just-In-Time Software Defect Prediction methods suffer from the data imbalance problem, where the majority class (normal commits) significantly outnumbers the minority class (buggy commits). This results in a higher probability of misclassification. Various data balancing techniques have been proposed to address this challenge with varying degrees of success. In this study, we propose an approach that rely on One-Class Classification (OCC) to train models using data from the majority class only. This eliminates the need for data balancing. We compare the accuracy of three OCC algorithms - One-class SVM, Isolation Forest, and One-class k-NN - to their binary counterparts - SVM, Random Forest, and k-NN - on 34 software projects. Our results show that the data imbalance ratio (the proportion of normal to buggy commits) plays a crucial role in determining the optimal classification approach. We found that for projects with medium to high imbalance ratio, OCC algorithms outperform binary classifiers with and without data balancing, using cross and time-sensitive validation approaches. Furthermore, we found that OCC methods require fewer features for projects with medium to high IR, reducing the computational overhead of training and response time while providing a better understanding of the data and algorithm behavior.

Improvement of Malicious Software Detection Accuracy through Genetic Programming Symbolic Classifier with Application of Dataset Oversampling Techniques

Malware detection using hybrid features, combining binary and hexadecimal analysis with DLL calls, is crucial for leveraging the strengths of both static and dynamic analysis methods. Artificial intelligence (AI) enhances this process by enabling automated pattern recognition, anomaly detection, and continuous learning, allowing security systems to adapt to evolving threats and identify complex, polymorphic malware that may exhibit varied behaviors. This synergy of hybrid features with AI empowers malware detection systems to efficiently and proactively identify and respond to sophisticated cyber threats in real time. In this paper, the genetic programming symbolic classifier (GPSC) algorithm was applied to the publicly available dataset to obtain symbolic expressions (SEs) that could detect the malware software with high classification performance. The initial problem with the dataset was a high imbalance between class samples, so various oversampling techniques were utilized to obtain balanced dataset variations on which GPSC was applied. To find the optimal combination of GPSC hyperparameter values, the random hyperparameter value search method (RHVS) was developed and applied to obtain SEs with high classification accuracy. The GPSC was trained with five-fold cross-validation (5FCV) to obtain a robust set of SEs on each dataset variation. To choose the best SEs, several evaluation metrics were used, i.e., the length and depth of SEs, accuracy score (ACC), area under receiver operating characteristic curve (AUC), precision, recall, f1-score, and confusion matrix. The best-obtained SEs are applied on the original imbalanced dataset to see if the classification performance is the same as it was on balanced dataset variations. The results of the investigation showed that the proposed method generated SEs with high classification accuracy (0.9962) in malware software detection.

Financial transaction fraud detector based on imbalance learning and graph neural network

Fraud detection is a vital and challenging task in the financial domain. Traditional machine learning approaches have limitations in dealing with the high imbalance and complexity of transaction data and the stealthy behavior of fraudulent entities. To address these issues, we propose HHLN-GNN, a graph neural network-based fraud detection model that leverages subgraph generators and neighborhood samplers to handle category imbalance. Furthermore, the model employs a self-attentive module and differentiates between homogeneous and heterogeneous connections to reduce the artificiality of fraudulent nodes and exploit the hidden information of transaction data more fully. We conduct experiments on three real-world public benchmark datasets, YelpChi, Amazon and Elliptic, and demonstrate that our model significantly outperforms existing benchmark methods on various performance metrics, such as F1-macro, AUC and GMean, by 10%, 12.5%, and 17.3% on YelpChi, 0.7%, 2.5% and 4% on Amazon, respectively.

ASE: Anomaly scoring based ensemble learning for highly imbalanced datasets

Nowadays, many classification algorithms have been applied to various industries to help them work out their problems met in real-life scenarios. However, in many binary classification tasks, samples in the minority class only make up a small part of all instances, which leads to the datasets we get usually suffer from high imbalance ratio. Existing models sometimes treat minority classes as noise or ignore them as outliers encountering data skewing. In order to solve this problem, we propose a bagging ensemble learning framework ASE (Anomaly Scoring Based Ensemble Learning). This framework has a scoring system based on anomaly detection algorithms which can guide the resampling strategy by divided samples in the majority class into subspaces. Then specific number of instances will be under-sampled from each subspace to construct subsets by combining with the minority class. And we calculate the weights of base classifiers trained by the subsets according to the classification result of the anomaly detection model and the statistics of the subspaces. Experiments have been conducted which show that our ensemble learning model can dramatically improve the performance of base classifiers and is more efficient than other existing methods under a wide range of imbalance ratio, data scale and data dimension. ASE can be combined with various classifiers and every part of our framework has been proved to be reasonable and necessary.

IRS-BAG-Integrated Radius-SMOTE Algorithm with Bagging Ensemble Learning Model for Imbalanced Data Set Classification

Imbalanced learning problems are a challenge faced by classifiers when data samples have an unbalanced distribution among classes. The Synthetic Minority Over-Sampling Technique (SMOTE) is one of the most well-known data pre-processing methods. Problems that arise when oversampling with SMOTE are the phenomenon of noise, small disjunct samples, and overfitting due to a high imbalance ratio in a dataset. A high level of imbalance ratio and low variance conditions cause the results of synthetic data generation to be collected in narrow areas and conflicting regions among classes and make them susceptible to overfitting during the learning process by machine learning methods. Therefore, this research proposes a combination between Radius-SMOTE and Bagging Algorithm called the IRS-BAG Model. For each sub-sample generated by bootstrapping, oversampling was done using Radius SMOTE. Oversampling on the sub-sample was likely to overcome overfitting problems that might occur. Experiments were carried out by comparing the performance of the IRS-BAG model with various previous oversampling methods using the imbalanced public dataset. The experiment results using three different classifiers proved that all classifiers had gained a notable improvement when combined with the proposed IRS-BAG model compared with the previous state-of-the-art oversampling methods. Doi: 10.28991/ESJ-2023-07-05-04 Full Text: PDF

Asymmetric gradient penalty based on power exponential function for imbalanced data classification

Model bias is a tricky problem in imbalanced data classification. An asymmetric gradient penalty method is proposed based on the power exponential function to alleviate this. The methodology integrates a power exponential function as a moderator into the cross-entropy loss of the negative samples, driving the model to focus on hesitant samples while ignoring easy and singular samples. The rationality of the algorithm is explored from the gradient point of view, and it is demonstrated that the approach improves focal loss and asymmetric focal loss. Then, the imbalanced data classification experiments were deployed on MNIST, CIFAR10, CIFAR100, and Caltech101, respectively. For binary classification, datasets with several imbalance ratios constituted by varying the sample size of the majority class and minority class are included in the experiments. In the multi-category classification experiments, we discuss imbalanced datasets with only a single majority category and those with several majority categories and examine step-imbalance datasets and linear-imbalance datasets. The results reveal that the proposed method exhibits competitiveness on various imbalanced datasets and better robustness on high imbalance ratio datasets. Finally, the approach is deployed on the pulsar candidate dataset HTRU, and the state-of-the-art results are yielded. Our code is available at https://github.com/gzmtzly/GPPE.

Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences

In this paper, we explore the effectiveness of the GPT-3 model in tackling imbalanced sentiment analysis, focusing on the Coursera online course review dataset that exhibits high imbalance. Training on such skewed datasets often results in a bias towards the majority class, undermining the classification performance for minority sentiments, thereby accentuating the necessity for a balanced dataset. Two primary initiatives were undertaken: (1) synthetic review generation via fine-tuning of the Davinci base model from GPT-3 and (2) sentiment classification utilizing nine models on both imbalanced and balanced datasets. The results indicate that good-quality synthetic reviews substantially enhance sentiment classification performance. Every model demonstrated an improvement in accuracy, with an average increase of approximately 12.76% on the balanced dataset. Among all the models, the Multinomial Naïve Bayes achieved the highest accuracy, registering 75.12% on the balanced dataset. This study underscores the potential of the GPT-3 model as a feasible solution for addressing data imbalance in sentiment analysis and offers significant insights for future research.

Therapeutic cancer vaccination against mutant calreticulin in myeloproliferative neoplasms induces expansion of specific T cells in the periphery but specific T cells fail to enrich in the bone marrow.

Therapeutic cancer vaccination against mutant calreticulin (CALR) in patients with CALR-mutant (CALRmut) myeloproliferative neoplasms (MPN) induces strong T-cell responses against mutant CALR yet fails to demonstrate clinical activity. Infiltration of tumor specific T cells into the tumor microenvironment is needed to attain a clinical response to therapeutic cancer vaccination. Determine if CALRmut specific T cells isolated from vaccinated patients enrich in the bone marrow upon completion of vaccination and explore possible explanations for the lack of enrichment. CALRmut specific T cells from four of ten vaccinated patients were expanded, enriched, and analyzed by T-cell receptor sequencing (TCRSeq). The TCRs identified were used as fingerprints of CALRmut specific T cells. Bone marrow aspirations from the four patients were acquired at baseline and at the end of trial. T cells were enriched from the bone marrow aspirations and analyzed by TCRSeq to identify the presence and fraction of CALRmut specific T cells at the two different time points. In silico calculations were performed to calculate the ratio between transformed cells and effector cells in patients with CALRmut MPN. The fraction of CALRmut specific T cells in the bone marrow did not increase upon completion of the vaccination trial. In general, the T cell repertoire in the bone marrow remains relatively constant through the vaccination trial. The enriched and expanded CALRmut specific T cells recognize peripheral blood autologous CALRmut cells. In silico analyses demonstrate a high imbalance in the fraction of CALRmut cells and CALRmut specific effector T-cells in peripheral blood. CALRmut specific T cells do not enrich in the bone marrow after therapeutic cancer peptide vaccination against mutant CALR. The specific T cells recognize autologous peripheral blood derived CALRmut cells. In silico analyses demonstrate a high imbalance between the number of transformed cells and CALRmut specific effector T-cells in the periphery. We suggest that the high burden of transformed cells in the periphery compared to the number of effector cells could impact the ability of specific T cells to enrich in the bone marrow.

From reactive to proactive load balancing for task‐based parallel applications in distributed memory machines

SummaryLoad balancing is often a challenge in task‐parallel applications. The balancing problems are divided into static and dynamic. “Static” means that we have some prior knowledge about load information and perform balancing before execution, while “dynamic” must rely on partial information of the execution status to balance the load at runtime. Conventionally, work stealing is a practical approach used in almost all shared memory systems. In distributed memory systems, the communication overhead can make stealing tasks too late. To improve, people have proposed a reactive approach to relax communication in balancing load. The approach leaves one dedicated thread per process to monitor the queue status and offload tasks reactively from a slow to a fast process. However, reactive decisions might be mistaken in high imbalance cases. First, this article proposes a performance model to analyze reactive balancing behaviors and understand the bound leading to incorrect decisions. Second, we introduce a proactive approach to improve further balancing tasks at runtime. The approach exploits task‐based programming models with a dedicated thread as well, namely . Nevertheless, the main idea is to force not only to monitor load; it will characterize tasks and train load prediction models by online learning. “Proactive” indicates offloading tasks before each execution phase proactively with an appropriate number of tasks at once to a potential victim (denoted by an underloaded/fast process). The experimental results confirm speedup improvements from to in important use cases compared to the previous solutions. Furthermore, this approach can support co‐scheduling tasks across multiple applications.